© 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. 34-GEMMASCOPE-RES-131K
    7. 117522
    Prev
    Next
    INDEX
    Explanations

    code and legal licenses

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

    the presence of numeric literals or digits in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    enswert
    -0.75
     Dash
    -0.72
     Raúl
    -0.69
    彅
    -0.69
    ここは
    -0.69
     traiter
    -0.68
    CONSIDER
    -0.68
    ländischen
    -0.67
     storyteller
    -0.67
    вы
    -0.65
    POSITIVE LOGITS
     OnTrigger
    0.70
    парат
    0.69
    ++){
    0.69
    DrawerLayout
    0.65
     frozen
    0.63
    iklet
    0.62
    ᅩ
    0.62
     cara
    0.62
    cartItems
    0.62
    ++)
    0.62
    Activations Density 0.059%

    No Known Activations