© 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. 44146
    Prev
    Next
    INDEX
    Explanations

    words after "The", "Dark", "Keep", "Best"

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

    code blocks and punctuation

    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
     vergangenen
    0.48
    ̈
    0.47
     dalších
    0.46
     wszystkich
    0.44
    ()-
    0.44
     principais
    0.44
     wichtigsten
    0.44
     ferr
    0.44
     carbonic
    0.44
    ίζουν
    0.43
    POSITIVE LOGITS
    መሪያ
    0.47
    ли
    0.45
     паз
    0.44
    코드
    0.42
    NaN
    0.42
    ПК
    0.42
    칼
    0.41
    wertung
    0.40
     minValue
    0.40
    го
    0.40
    Activations Density 0.000%

    No Known Activations