© 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. 114714
    Prev
    Next
    INDEX
    Explanations

    paid for items or training

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

    dangerous situation

    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
    åg
    0.51
    welt
    0.47
     jugador
    0.46
    embry
    0.46
     Embry
    0.46
     freien
    0.46
     giocatore
    0.45
    늑
    0.45
     সেকেন্ড
    0.44
     मुक्त
    0.43
    POSITIVE LOGITS
    ziemy
    0.47
     zgodnie
    0.46
     baš
    0.45
    rani
    0.44
     Shet
    0.43
     congenial
    0.43
     ஏனெ
    0.42
     lalu
    0.41
    ாதார
    0.41
     Smiths
    0.41
    Activations Density 0.000%

    No Known Activations