© 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. 175985
    Prev
    Next
    INDEX
    Explanations

    discovered that

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

    knowledge cut-off date

    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
     gums
    0.48
     potom
    0.48
     או
    0.45
     e
    0.45
     piloto
    0.44
     alebo
    0.43
     tryp
    0.43
    쟈
    0.42
     produk
    0.42
     पॅ
    0.42
    POSITIVE LOGITS
     уйнарга
    0.49
     कहने
    0.47
    <unused81>
    0.46
    悱
    0.46
     अभ्यर्थ
    0.45
    也就是说
    0.45
    punctuation
    0.44
     उल्लंघन
    0.44
     کھیلنے
    0.43
    အချိန်
    0.43
    Activations Density 0.001%

    No Known Activations