© 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. 154502
    Prev
    Next
    INDEX
    Explanations

    after description

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

    proper nouns followed by verbs

    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
     Erfolg
    0.47
     Informationen
    0.46
     anal
    0.45
     or
    0.45
     oder
    0.45
    2
    0.45
    1
    0.44
     elenc
    0.42
     Ł
    0.42
     kinds
    0.42
    POSITIVE LOGITS
    ミス
    0.55
    መስ
    0.53
    感じです
    0.52
    ޚ
    0.50
    علی
    0.50
     समय
    0.49
     علی
    0.49
    मेरी
    0.49
     उत्तरी
    0.48
     டிவி
    0.48
    Activations Density 0.000%

    No Known Activations