© 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. 95982
    Prev
    Next
    INDEX
    Explanations

    receive payment or aid

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

    informed about others

    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
    Ꮒ
    0.46
    ますが
    0.46
     हिस्सा
    0.45
    つつ
    0.44
    ם
    0.43
    诡
    0.42
    一定要
    0.42
    ຢ
    0.41
    μή
    0.40
    ມີ
    0.40
    POSITIVE LOGITS
    at
    0.50
    conversion
    0.50
    administrative
    0.50
    cow
    0.47
    Structured
    0.47
    imbo
    0.47
    orgement
    0.46
     প্রাপ
    0.46
    Cow
    0.45
    aid
    0.45
    Activations Density 0.001%

    No Known Activations