© 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. 28175
    Prev
    Next
    INDEX
    Explanations

    illustrated by, intended to, example of

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

    actions and outcomes

    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
     detention
    0.45
     olan
    0.44
     incorrectly
    0.44
     sicurezza
    0.44
    дій
    0.44
    ↵
    0.43
     cases
    0.42
    ید
    0.42
    ﺔ
    0.41
     follow
    0.41
    POSITIVE LOGITS
     émotion
    0.46
     воспомина
    0.45
     சின்னமாக
    0.45
     அலங்க
    0.45
    转型
    0.45
     얼굴
    0.44
    idazol
    0.44
    怎样的
    0.43
     фраг
    0.43
     immunohist
    0.42
    Activations Density 0.000%

    No Known Activations