© 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. 54962
    Prev
    Next
    INDEX
    Explanations

    data and contracts

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

    parameters and GPT models

    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
    LoopBlend
    0.45
    Mar
    0.45
    Waiter
    0.43
    ♀
    0.43
    Q
    0.43
    Mara
    0.43
    वळ
    0.42
    Bbb
    0.42
    Rita
    0.42
     leftover
    0.42
    POSITIVE LOGITS
     வெப்சீரி
    0.57
    सारी
    0.51
    튠
    0.48
     restauración
    0.47
     தனி
    0.46
     alcun
    0.46
     Ovaj
    0.46
    renew
    0.46
     ابنائي
    0.46
     அவர்களின்
    0.46
    Activations Density 0.000%

    No Known Activations