© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70053
    Prev
    Next
    INDEX
    Explanations

    game mods and software mods

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

    The neuron activates on occurrences of “mod” (and related forms like “modding,” “mods,” “Mod Organizer,” etc.) and associated numerical version or loader tokens.

    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
    "
    -2.44
     In
    -2.13
    at
    -2.13
     through
    -2.02
     one
    -1.99
    !!!!!
    -1.97
     Even
    -1.93
     plethora
    -1.92
     Not
    -1.91
     striving
    -1.88
    POSITIVE LOGITS
     maniere
    2.06
     抠
    2.03
     deliciously
    2.03
     sinyal
    2.03
    筇
    2.02
    媜
    2.02
     avances
    2.00
     tunik
    1.98
    鉏
    1.98
     inget
    1.95
    Activations Density 0.017%

    No Known Activations