© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 193444
    Prev
    Next
    INDEX
    Explanations

    anything and locations

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

    predicting descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imageUrl
    0.48
    Só
    0.48
    Ба
    0.46
    谄
    0.46
    Ка
    0.45
    íguez
    0.45
    菈
    0.45
     متنوع
    0.45
    Unsupported
    0.44
    Enlaces
    0.44
    POSITIVE LOGITS
     and
    0.55
    i
    0.53
     slain
    0.46
     fighting
    0.45
     yeniden
    0.45
     works
    0.45
     killing
    0.44
     yu
    0.43
     dritten
    0.43
     yuk
    0.43
    Activations Density 0.000%

    No Known Activations