© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 204667
    Prev
    Next
    INDEX
    Explanations

    accept higher, not the, but also

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    纭
    0.52
    ärt
    0.49
     Agreements
    0.46
     стали
    0.45
    ành
    0.43
     jurídica
    0.43
    ваясь
    0.43
    uiDesigner
    0.43
    uern
    0.42
     féri
    0.42
    POSITIVE LOGITS
     eradic
    0.44
     coupling
    0.44
     قيمة
    0.43
    مد
    0.42
     [*
    0.42
     chronicle
    0.41
     പു
    0.40
     अधिक
    0.40
    Suff
    0.40
    calcul
    0.40
    Activations Density 0.011%

    No Known Activations