© 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. 174126
    Prev
    Next
    INDEX
    Explanations

    hailed as hero

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

    control buttons

    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
     WHICH
    0.52
    ↵
    0.52
    THIS
    0.51
    ENDS
    0.51
    ט
    0.51
    PLEASE
    0.49
    ir
    0.48
    门
    0.47
     welches
    0.47
    л
    0.47
    POSITIVE LOGITS
     घोड़
    0.52
     hòa
    0.46
     sillonné
    0.45
     институ
    0.45
    𐰚
    0.44
    ingale
    0.44
    fraud
    0.43
     स्थिर
    0.43
    aphor
    0.42
    agod
    0.42
    Activations Density 0.000%

    No Known Activations