© 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. 243360
    Prev
    Next
    INDEX
    Explanations

    withdrawal of, unable to, send over

    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
     commodo
    0.48
    켰
    0.48
     opinion
    0.44
     kursi
    0.44
     trium
    0.44
     locale
    0.43
    ญิง
    0.43
    Foo
    0.43
     Foo
    0.43
     wilderness
    0.42
    POSITIVE LOGITS
     ／
    0.48
    ）・
    0.47
    ಿಗಳು
    0.47
    ontan
    0.46
     continúa
    0.45
    ત્મ
    0.45
     すぎ
    0.43
    でお
    0.42
    ông
    0.42
    asak
    0.42
    Activations Density 0.001%

    No Known Activations