© 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. 59708
    Prev
    Next
    INDEX
    Explanations

    and others like

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

    developing independence or panic attacks

    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
     RELEASE
    0.46
    ذ
    0.45
    群
    0.44
    全程
    0.44
    ళ
    0.43
    њ
    0.43
    ด้
    0.43
    强制
    0.43
    标记
    0.43
    队的
    0.42
    POSITIVE LOGITS
    skim
    0.49
    urlencoded
    0.49
    strawberry
    0.48
     gotovo
    0.48
    might
    0.47
    AttributedString
    0.47
     opini
    0.46
    senal
    0.46
    コーヒー
    0.46
    someone
    0.46
    Activations Density 0.000%

    No Known Activations