© 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. 208902
    Prev
    Next
    INDEX
    Explanations

    technical terms and unicode

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

    different types of diversity

    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
     fantastic
    0.56
     x
    0.52
    tan
    0.51
    yak
    0.51
     collagen
    0.50
     fantast
    0.50
     Volunteer
    0.50
    mu
    0.48
     quienes
    0.48
    ile
    0.46
    POSITIVE LOGITS
    場合
    0.48
    וף
    0.46
    RetResult
    0.46
    стройства
    0.43
    شر
    0.43
    خرج
    0.43
    ד
    0.43
    莎
    0.43
    تباط
    0.42
    Paf
    0.42
    Activations Density 0.000%

    No Known Activations