© 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. 217662
    Prev
    Next
    INDEX
    Explanations

    security updates, gift note, Brooklyn events

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

    coding, programming, and technical explanations

    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
    uştur
    0.45
     ϒ
    0.44
    Cola
    0.43
     Tahun
    0.43
    Bias
    0.42
    组成
    0.42
    킹
    0.42
    Eid
    0.41
     Свя
    0.40
    T
    0.40
    POSITIVE LOGITS
    疣
    0.52
     enzimas
    0.44
    álního
    0.44
     racional
    0.44
    առ
    0.44
     molestias
    0.43
     festivities
    0.43
     financiar
    0.43
     cystic
    0.42
    ภัย
    0.42
    Activations Density 0.000%

    No Known Activations