© 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. 85984
    Prev
    Next
    INDEX
    Explanations

    services, worksheet, difference, parts, tools

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

    contrasting items or ideas

    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
    社会
    0.51
    遡
    0.48
    哲学
    0.48
    收入
    0.47
     carbono
    0.46
    容量
    0.46
    趣味
    0.45
    しているので
    0.45
    者の
    0.44
     pathologies
    0.44
    POSITIVE LOGITS
     akad
    0.46
     워
    0.45
    ched
    0.42
    dar
    0.41
    inj
    0.41
     두
    0.41
     퍼
    0.41
    dauer
    0.41
    였습니다
    0.41
    дар
    0.41
    Activations Density 0.000%

    No Known Activations