© 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. 280
    Prev
    Next
    INDEX
    Explanations

    fresh fruit juice

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

    provide and execute actions

    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
    ing
    0.55
     Star
    0.49
    aise
    0.49
    ican
    0.48
     ia
    0.48
     be
    0.48
    U
    0.47
    icates
    0.46
    ally
    0.46
    en
    0.46
    POSITIVE LOGITS
    мл
    0.57
    鼕
    0.56
     garantire
    0.55
    μμ
    0.51
     REQUIRED
    0.51
    日時
    0.50
    л
    0.50
     richiest
    0.49
    ټر
    0.49
    ч
    0.49
    Activations Density 0.000%

    No Known Activations