© 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. 64774
    Prev
    Next
    INDEX
    Explanations

    online platforms after "on"

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

    rendered fat

    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
    த்திற்காக
    0.45
    క్షణ
    0.43
     সুন্দর
    0.43
     FileName
    0.43
     {}>,
    0.42
    ियोग्राफी
    0.42
     પોતાના
    0.42
    SafeArea
    0.41
    ⾯
    0.41
    రికీ
    0.41
    POSITIVE LOGITS
    prise
    0.43
    implemented
    0.43
    ซ
    0.42
    <0x84>
    0.42
    Hamlet
    0.41
    *
    0.41
    صد
    0.40
    سر
    0.39
    ود
    0.39
    ยว
    0.39
    Activations Density 0.000%

    No Known Activations