© 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. 182002
    Prev
    Next
    INDEX
    Explanations

    even creates or came

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

    negations and limitations

    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
    ל
    0.46
    imposed
    0.46
    ౌ
    0.44
    哭
    0.44
    orph
    0.44
    受信
    0.44
    gob
    0.43
    磷
    0.43
    癸
    0.43
    किस
    0.42
    POSITIVE LOGITS
     aficionados
    0.55
     frigor
    0.53
     bâ
    0.51
     houseplants
    0.48
     掛け
    0.48
     gérer
    0.48
     conveniences
    0.47
     vru
    0.47
     kıl
    0.46
     കൈ
    0.46
    Activations Density 0.001%

    No Known Activations