© 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. 35836
    Prev
    Next
    INDEX
    Explanations

    reach several, County Sports, minimum score, up 4%

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

    receiving updates or status

    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
    ణ
    0.45
     настолько
    0.41
     मोठी
    0.41
    ต่ำ
    0.40
    น
    0.40
    亢
    0.40
     मीडिया
    0.39
    ই
    0.38
    囝
    0.38
    什么样的
    0.38
    POSITIVE LOGITS
    orit
    0.42
    agine
    0.39
    conde
    0.39
    ouri
    0.39
    imread
    0.38
     purification
    0.37
    atschapp
    0.37
    unia
    0.36
    urname
    0.36
    ushima
    0.36
    Activations Density 0.000%

    No Known Activations