© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 14920
    Prev
    Next
    INDEX
    Explanations

    banging my head

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly responds to words in the idiom “banging my head against the wall,” i.e. first-person expressions of frustration using “banging,” “head,” “against,” “wall,” etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     then
    -2.14
     <",
    -1.44
    -_
    -1.40
     tena
    -1.38
     tsy
    -1.37
    ;-)
    -1.32
     fars
    -1.31
    ang
    -1.30
    ts
    -1.29
    -..
    -1.29
    POSITIVE LOGITS
     هذه
    1.53
     también
    1.52
     estos
    1.47
     даже
    1.45
    hoodie
    1.41
     with
    1.33
    ilización
    1.30
     hosszú
    1.30
     resembled
    1.27
    либо
    1.27
    Activations Density 0.182%

    No Known Activations