© 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. 44972
    Prev
    Next
    INDEX
    Explanations

    available around

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

    URLs and code snippets

    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
    ↵
    0.33
    <0xE2>
    0.30
    <h3>
    0.30
    ı
    0.29
    u
    0.29
    >
    0.27
    ↵↵
    0.27
    ．
    0.26
    i
    0.26
    uk
    0.26
    POSITIVE LOGITS
    SegmentInfo
    0.27
     oxides
    0.26
     nymph
    0.24
     nymphs
    0.24
    িতাম
    0.24
    Pyrazole
    0.24
    тной
    0.23
    щены
    0.23
    шена
    0.23
    چھا
    0.23
    Activations Density 0.006%

    No Known Activations