© 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. 53498
    Prev
    Next
    INDEX
    Explanations

    numbers and phrases

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

    miniature billiard balls

    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
     exploración
    0.48
     છેલ્લા
    0.48
     层
    0.48
     হেন
    0.47
     vuccanti
    0.47
     récente
    0.46
     récentes
    0.45
     INDUSTR
    0.44
    íta
    0.44
     ఆరోగ
    0.43
    POSITIVE LOGITS
    0
    0.48
    야
    0.44
    ギ
    0.43
    pm
    0.43
    අ
    0.42
    K
    0.41
    PM
    0.41
    海洋
    0.41
    ラリー
    0.41
    rael
    0.40
    Activations Density 0.000%

    No Known Activations