© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101908
    Prev
    Next
    INDEX
    Explanations

    inverters neighbourhood

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

    The neuron fires strongly on words ending in the suffix “-ers” (and occasionally the variant “-ero”).

    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
    ون
    -2.80
    ם
    -2.59
    juries
    -2.52
    or
    -2.47
    ter
    -2.42
    mm
    -2.39
    اً
    -2.38
    ty
    -2.36
    ah
    -2.33
    м
    -2.30
    POSITIVE LOGITS
    ة
    2.66
    istocene
    2.42
    俛
    2.31
    虓
    2.27
     hatte
    2.22
    ing
    2.20
    ية
    2.17
     mereka
    2.14
    휀
    2.13
    ⢮
    2.11
    Activations Density 0.015%

    No Known Activations