© 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. 30880
    Prev
    Next
    INDEX
    Explanations

    scores relative to par

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

    scores and records

    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
    autorité
    0.44
     abraz
    0.42
    에게
    0.42
    membre
    0.42
     prophe
    0.40
    ⌜
    0.39
    ając
    0.39
    ньше
    0.39
    autoarima
    0.39
     ძალი
    0.39
    POSITIVE LOGITS
     reduction
    0.46
     scores
    0.42
     score
    0.40
     integers
    0.40
    ወ
    0.40
    Scores
    0.39
     Reduction
    0.38
    р
    0.38
    Reduction
    0.38
     रु
    0.38
    Activations Density 0.016%

    No Known Activations