© 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. 189974
    Prev
    Next
    INDEX
    Explanations

    specialist, Perl, antagonists

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

    functional clothing. advisor. crime. problems

    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
    每次
    0.45
    らない
    0.44
     botella
    0.44
     पौधों
    0.41
     সঙ্কট
    0.41
     SPARSE
    0.41
    ,]$
    0.41
    itación
    0.40
     নেতারা
    0.39
    텐
    0.39
    POSITIVE LOGITS
     pubblica
    0.46
     Einf
    0.46
    λασ
    0.45
    ScreenBinding
    0.45
     ricost
    0.45
     亠
    0.45
    യായി
    0.44
    outputPath
    0.44
    ========
    0.44
     związane
    0.44
    Activations Density 0.001%

    No Known Activations