© 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. 100829
    Prev
    Next
    INDEX
    Explanations

    terms, rules, and conditions

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

    read_line(&mut item)

    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
    }
    0.52
    ></
    0.51
    ৭
    0.49
    ww
    0.48
    YPE
    0.46
    />
    0.46
     undergrad
    0.46
     STYLE
    0.45
    _
    0.45
    Mixin
    0.44
    POSITIVE LOGITS
     تلیفون
    0.53
     povos
    0.49
     چې
    0.47
     سبيل
    0.46
     penilaian
    0.46
     တယ်
    0.46
     lunghezza
    0.46
     ponctués
    0.45
     宮
    0.45
     atteinte
    0.45
    Activations Density 0.001%

    No Known Activations