© 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. 87807
    Prev
    Next
    INDEX
    Explanations

    methods and results

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

    fine tuning viability

    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
    7
    0.52
    女主
    0.47
    中に
    0.46
    噤
    0.46
    新品
    0.46
     新
    0.46
    犯罪
    0.46
    larni
    0.45
    🛰
    0.45
     көр
    0.45
    POSITIVE LOGITS
     analyzers
    0.58
     ointment
    0.52
     regimens
    0.52
     ዘዴ
    0.51
     preservatives
    0.49
     interpreters
    0.49
     multiplicative
    0.48
     variabili
    0.47
     additives
    0.47
     capillaries
    0.47
    Activations Density 0.000%

    No Known Activations