© 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. 52756
    Prev
    Next
    INDEX
    Explanations

    press release

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

    FOR IMMEDIATE RELEASE

    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
    debut
    0.44
     Director
    0.44
    Director
    0.44
     chiefly
    0.42
    .
    0.41
     dismissal
    0.40
     Solicitor
    0.40
     closed
    0.39
    .(
    0.39
     circunst
    0.39
    POSITIVE LOGITS
    缩小
    0.49
    ىن
    0.44
    执
    0.44
    వ
    0.43
    棉
    0.43
    ਿੰ
    0.43
    ారె
    0.43
    产业
    0.42
    镕
    0.42
    城的
    0.42
    Activations Density 0.000%

    No Known Activations