© 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. 115484
    Prev
    Next
    INDEX
    Explanations

    horse racing saddles

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

    punctuation and code delimiters

    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
     डाइ
    0.49
    tense
    0.47
    ı
    0.47
    ॉन
    0.46
    um
    0.44
     خانو
    0.43
    alte
    0.42
    ains
    0.42
    atum
    0.42
    ی
    0.42
    POSITIVE LOGITS
     votes
    0.56
     as
    0.53
     ipotesi
    0.52
     in
    0.51
     pays
    0.48
     zodiac
    0.47
     ballots
    0.47
     கட்சி
    0.47
     voted
    0.47
     song
    0.46
    Activations Density 0.001%

    No Known Activations