© 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. 169445
    Prev
    Next
    INDEX
    Explanations

    careers and hero stories

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

    life mission and living with intention

    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
    iculaire
    0.54
     மகளிர்
    0.47
    ето
    0.46
    ටි
    0.46
     Еў
    0.45
    绀
    0.45
    ТИ
    0.45
     симво
    0.43
     اثنين
    0.43
     беше
    0.42
    POSITIVE LOGITS
    raj
    0.52
     COMPLET
    0.46
     realistic
    0.46
    /////////////
    0.45
    ////////////////
    0.44
    dados
    0.44
     preju
    0.43
     sorprend
    0.43
     Bh
    0.43
    retti
    0.43
    Activations Density 0.001%

    No Known Activations