© 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. 195713
    Prev
    Next
    INDEX
    Explanations

    discussion of content like this

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

    technical terms and concepts

    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
     bunlar
    0.46
    这些人
    0.45
    <unused42>
    0.44
     bunları
    0.43
     bhavanti
    0.41
     использоваться
    0.41
    かわらず
    0.41
    ystycz
    0.40
     городских
    0.40
    }^{*}$
    0.40
    POSITIVE LOGITS
    complete
    0.45
     complete
    0.44
    jun
    0.43
    duplicate
    0.43
    "),(
    0.41
    toy
    0.40
    utter
    0.40
    mostrar
    0.40
     mostrar
    0.40
    er
    0.39
    Activations Density 0.001%

    No Known Activations