© 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. 14794
    Prev
    Next
    INDEX
    Explanations

    works through

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

    religious duty, system configuration, hidden states, monthly cycles

    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
    <h5>
    0.57
    <h4>
    0.57
    it
    0.47
    Tot
    0.47
    categories
    0.46
    Sr
    0.46
    d
    0.46
    ut
    0.45
    comments
    0.45
     SRP
    0.44
    POSITIVE LOGITS
    ГА
    0.51
     puestos
    0.48
    ành
    0.47
    ượu
    0.47
     posición
    0.46
     punished
    0.46
     vũ
    0.45
     asesin
    0.45
     ان
    0.45
    पर्यंत
    0.44
    Activations Density 0.000%

    No Known Activations