© 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. 196356
    Prev
    Next
    INDEX
    Explanations

    headboard or crib

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

    bedside objects

    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
     ngồi
    0.49
     乗
    0.47
    コーヒー
    0.43
     コーヒー
    0.42
     kı
    0.42
     搭
    0.42
     slack
    0.41
     দেহের
    0.41
     OSA
    0.41
    hö
    0.40
    POSITIVE LOGITS
    naissance
    0.48
    男生
    0.46
    性别
    0.45
     αγο
    0.44
    bedroom
    0.44
    createSprite
    0.43
    igger
    0.43
    avorable
    0.42
    gender
    0.42
    ᆫ
    0.41
    Activations Density 0.096%

    No Known Activations