© 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. 160203
    Prev
    Next
    INDEX
    Explanations

    registered, download, risk, annual, preparation, United, opera, gala, calorimeter

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

    risk minimization, strategy execution, signaling, task handling

    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
    aram
    0.48
     Minerals
    0.45
    Пре
    0.44
    gment
    0.44
     Pow
    0.44
     তফস
    0.44
    корд
    0.43
    㷅
    0.42
    cord
    0.42
     Cord
    0.42
    POSITIVE LOGITS
     avem
    0.52
    ൦
    0.49
     infestation
    0.46
    ל
    0.44
     recou
    0.43
    FARE
    0.43
     thing
    0.43
     THINGS
    0.42
    回收
    0.41
     esclav
    0.41
    Activations Density 0.000%

    No Known Activations