© 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. 150276
    Prev
    Next
    INDEX
    Explanations

    capacity, limits, or specific roles

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

    live in / customer orders / understand you

    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
    াইব
    0.44
    物
    0.43
    lá
    0.43
     ,
    0.42
    jó
    0.41
    量
    0.41
     lente
    0.40
    lad
    0.40
    né
    0.40
    refixer
    0.40
    POSITIVE LOGITS
    अर्
    0.55
     σημα
    0.48
     bagus
    0.46
    𝖺
    0.46
    <0x80>
    0.46
    媜
    0.45
    gung
    0.45
    apadani
    0.44
    engelsk
    0.43
     დიდ
    0.43
    Activations Density 0.001%

    No Known Activations