© 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. 137989
    Prev
    Next
    INDEX
    Explanations

    ended

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

    prioritization of certain themes

    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
    ᱘
    0.55
     auch
    0.53
     anche
    0.49
     ạ
    0.48
     Hochzeit
    0.48
    人在
    0.46
     Sancho
    0.46
    ánica
    0.46
     GS
    0.45
     циф
    0.45
    POSITIVE LOGITS
    Support
    0.53
    Dys
    0.51
    Limit
    0.51
    दियों
    0.49
    Shutdown
    0.48
    Limits
    0.48
    Spacer
    0.48
    ᄎ
    0.48
    Skin
    0.48
    Sweden
    0.46
    Activations Density 0.000%

    No Known Activations