© 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. 107302
    Prev
    Next
    INDEX
    Explanations

    without warranty of any kind

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

    technical specifications and categories

    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
    idi
    0.49
    Nella
    0.49
    Utt
    0.47
    4
    0.46
     경우
    0.45
    very
    0.44
    similarity
    0.44
    kPa
    0.44
    Nell
    0.43
    May
    0.43
    POSITIVE LOGITS
    鏘
    0.46
     hígado
    0.46
     polymorphisms
    0.45
    DOCTYPE
    0.44
     περιο
    0.44
    ovao
    0.43
     servidor
    0.43
     puc
    0.43
     CONST
    0.43
     parac
    0.43
    Activations Density 0.000%

    No Known Activations