© 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. 49947
    Prev
    Next
    INDEX
    Explanations

    numbers and descriptions

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

    gameplay, mechanics, programming, science

    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
    施設の
    0.53
    qPCR
    0.49
     öğrenciler
    0.47
     sanitaria
    0.46
     operativa
    0.45
    ἱ
    0.43
     servizi
    0.42
     guérison
    0.42
     پرورش
    0.42
     ChatGPT
    0.41
    POSITIVE LOGITS
    originals
    0.47
     जानी
    0.46
    ia
    0.44
     have
    0.43
    have
    0.43
    強
    0.43
    ॐ
    0.42
    WOOD
    0.42
     डिजाइन
    0.41
     handels
    0.41
    Activations Density 0.000%

    No Known Activations