© 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. 66781
    Prev
    Next
    INDEX
    Explanations

    organisation adjusted

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

    Project Settings, Dress Code

    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
    getStartState
    0.42
    crazy
    0.41
    <0x99>
    0.40
     روم
    0.39
     نام
    0.37
     نامه
    0.37
     நிச்சயம்
    0.36
     داش
    0.36
    textField
    0.36
    centos
    0.36
    POSITIVE LOGITS
    谆
    0.51
    ował
    0.51
     szko
    0.50
    inud
    0.49
    悆
    0.49
     leyenda
    0.48
     لله
    0.48
     okula
    0.48
     légende
    0.48
     koju
    0.47
    Activations Density 0.001%

    No Known Activations