© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 78081
    Prev
    Next
    INDEX
    Explanations

    refuse to continue harmful content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ρα
    0.51
    Cou
    0.46
    A
    0.46
    Raw
    0.45
    Pl
    0.44
    De
    0.43
    hou
    0.43
    ედა
    0.43
    H
    0.43
    <0xB3>
    0.43
    POSITIVE LOGITS
    <unused37>
    0.49
     Invitational
    0.49
     município
    0.46
     Srps
    0.46
     alkoh
    0.45
     invito
    0.45
    ানোর
    0.44
    uraea
    0.44
     sends
    0.43
     gönd
    0.43
    Activations Density 0.007%

    No Known Activations