© 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. 155054
    Prev
    Next
    INDEX
    Explanations

    dates and times

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

    niche down specialization

    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
    fea
    0.44
    ]-
    0.44
    ct
    0.42
     businessman
    0.42
     wszyst
    0.42
    isph
    0.41
     spirito
    0.41
     muziek
    0.40
    ]-\
    0.40
     இளைஞ
    0.40
    POSITIVE LOGITS
     WrestleMania
    0.45
    积
    0.45
    花园
    0.44
     거지
    0.44
    韦
    0.44
    工厂
    0.43
    纽约
    0.42
    点击
    0.42
    테
    0.42
     Harold
    0.42
    Activations Density 0.001%

    No Known Activations