© 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. 180818
    Prev
    Next
    INDEX
    Explanations

    inspiration, simple, record, recorded, regular, regarding

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

    specific measure

    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
    மனித
    0.57
    ט
    0.53
    সুতরাং
    0.52
     ovako
    0.51
    ಸ
    0.51
    ன்
    0.51
    Anche
    0.50
    жити
    0.50
    ג
    0.50
    사람
    0.50
    POSITIVE LOGITS
     country
    0.49
     combined
    0.49
     Quaker
    0.48
     Country
    0.46
     ((
    0.46
     SS
    0.46
     received
    0.45
     boys
    0.45
     i
    0.45
     IQ
    0.45
    Activations Density 0.001%

    No Known Activations