© 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. 156236
    Prev
    Next
    INDEX
    Explanations

    punctuations and common connectors

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

    types of

    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
     prohibitions
    0.50
    to
    0.47
     multival
    0.45
     limita
    0.43
    became
    0.42
     practicable
    0.42
     `:
    0.41
     prohibition
    0.41
     postice
    0.41
     jas
    0.40
    POSITIVE LOGITS
    ish
    0.45
    ális
    0.45
    淦
    0.44
    晎
    0.44
    鏄
    0.43
    φέρει
    0.42
    icuous
    0.42
    राट
    0.42
    审美
    0.42
     shitty
    0.41
    Activations Density 0.000%

    No Known Activations