© 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. 98668
    Prev
    Next
    INDEX
    Explanations

    May Day holidays

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

    interacting with me

    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
    ่านั้น
    0.47
    强调
    0.46
    कह
    0.44
    ן
    0.44
    DEBUGFS
    0.44
    כר
    0.44
    槟
    0.43
    კო
    0.43
     icy
    0.43
    िड
    0.42
    POSITIVE LOGITS
    ጇ
    0.55
     imping
    0.49
     derivados
    0.48
     referentes
    0.46
    matte
    0.46
    etera
    0.45
     durant
    0.45
     durante
    0.44
     relatifs
    0.44
     attaqu
    0.44
    Activations Density 0.001%

    No Known Activations