© 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. 208951
    Prev
    Next
    INDEX
    Explanations

    superhero novel

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

    unparalleled track record

    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
     ውሃ
    0.59
    soort
    0.58
    റ്റ
    0.51
    ア
    0.50
    ｸ
    0.49
    イン
    0.49
     individus
    0.49
    でお
    0.48
    區域
    0.48
     عباره
    0.47
    POSITIVE LOGITS
     Superhero
    0.43
    लेज
    0.41
    讶
    0.41
     superhero
    0.40
    Stage
    0.40
    चानक
    0.40
     añad
    0.40
    Novel
    0.39
    ****/
    0.39
    Superhero
    0.38
    Activations Density 0.001%

    No Known Activations