© 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. 74166
    Prev
    Next
    INDEX
    Explanations

    personal activities and family

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

    Social interaction & psychological issues

    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
    𝘫
    0.54
    ᒻ
    0.52
    ונ
    0.51
    LAGAB
    0.48
    ዴ
    0.48
    یکا
    0.48
    botao
    0.48
    イ
    0.47
    𝖽
    0.47
    ན
    0.47
    POSITIVE LOGITS
     were
    0.54
     had
    0.48
     amateur
    0.47
     a
    0.46
     stranded
    0.45
    ;
    0.44
     children
    0.43
     kids
    0.43
     contaminants
    0.43
     honors
    0.43
    Activations Density 0.000%

    No Known Activations