© 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. 22-GEMMASCOPE-RES-131K
    4. 72960
    Prev
    Next
    INDEX
    Explanations

    javascript file endings

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

    The neuron never fires—i.e. it doesn’t respond to any token (a “dead” neuron).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     for
    -2.00
     by
    -1.45
     with
    -1.44
     to
    -1.41
     a
    -1.30
     if
    -1.20
    焖
    -1.19
     doesn
    -1.15
    一定的
    -1.14
     plaît
    -1.09
    POSITIVE LOGITS
     vær
    1.27
     partager
    1.18
    lawesi
    1.15
     paliwa
    1.14
     recarg
    1.11
     cantidades
    1.09
     ouvrir
    1.08
     çantası
    1.07
     schloss
    1.06
     redé
    1.05
    Activations Density 0.005%

    No Known Activations