© 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. 235047
    Prev
    Next
    INDEX
    Explanations

    proactive+ reviews

    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
    ear
    0.57
    i
    0.55
    she
    0.51
    osti
    0.48
    y
    0.46
    schol
    0.46
    ,
    0.46
    elegant
    0.45
    gran
    0.45
     /
    0.44
    POSITIVE LOGITS
    ບບ
    0.52
     గొప్ప
    0.52
     coffers
    0.52
    بوط
    0.49
     comprimento
    0.49
     знал
    0.49
    ους
    0.48
     tốt
    0.48
    ब्ब
    0.48
    َاب
    0.47
    Activations Density 0.000%

    No Known Activations