© 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. 73893
    Prev
    Next
    INDEX
    Explanations

    consists of

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

    internet data sources

    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
    合理的
    0.48
     ജോലി
    0.47
    និយ
    0.41
     Planets
    0.41
     করেননি
    0.40
    凤
    0.40
     niemals
    0.40
     نريد
    0.39
    鸳
    0.39
    就不会
    0.39
    POSITIVE LOGITS
    בוע
    0.46
    🎂
    0.43
    ೇಖ
    0.43
     gotta
    0.41
     பட
    0.41
    🥃
    0.39
     copper
    0.38
     bulletins
    0.38
    tcpHeader
    0.38
    個セット
    0.38
    Activations Density 0.000%

    No Known Activations