© 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. 23704
    Prev
    Next
    INDEX
    Explanations

    property owned by

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

    content repurposing

    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
     candid
    0.44
    aktadır
    0.44
    ுடன்
    0.42
     ansible
    0.42
    രിക്കും
    0.42
     Midway
    0.41
     droid
    0.41
    </sup>
    0.41
     demonic
    0.41
     casks
    0.40
    POSITIVE LOGITS
    STATEMENT
    0.51
    statement
    0.49
    忶
    0.48
    listBox
    0.48
    வந்த
    0.47
    statements
    0.47
     اجازه
    0.47
    打印
    0.46
    parameter
    0.46
    ELL
    0.46
    Activations Density 0.000%

    No Known Activations