© 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. 12237
    Prev
    Next
    INDEX
    Explanations

    location, neighborhood, coast, Marcel, mark

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

    left, right, 2, red, black

    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
    ัล
    0.57
    ד
    0.51
    ร
    0.50
    ܂
    0.49
    ฟ
    0.48
    ྰ
    0.48
    Ꮹ
    0.47
    ༔
    0.47
     трёх
    0.46
    ริกา
    0.46
    POSITIVE LOGITS
     also
    0.57
     provides
    0.57
     was
    0.52
     serves
    0.52
     is
    0.52
     from
    0.50
     continues
    0.50
     brings
    0.49
     took
    0.48
     helped
    0.46
    Activations Density 0.010%

    No Known Activations