© 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. 188282
    Prev
    Next
    INDEX
    Explanations

    diverse languages and symbols

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

    restrictions and freedom

    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
     invertebrate
    0.47
    रन
    0.45
    టానికి
    0.45
    σε
    0.44
    "):
    0.44
    使用的
    0.44
    verm
    0.43
    טח
    0.43
    на
    0.42
    Inbox
    0.42
    POSITIVE LOGITS
     gustaría
    0.52
     límites
    0.52
     séparation
    0.51
     buồn
    0.51
     戦
    0.50
    𝘪
    0.49
     গোপন
    0.49
     possibilité
    0.48
     همان
    0.48
    ີ່
    0.48
    Activations Density 0.000%

    No Known Activations