© 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. 199686
    Prev
    Next
    INDEX
    Explanations

    lists of numbers and punctuation

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

    prohibited topics like cooking people

    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
     Determination
    0.45
     détermination
    0.45
     lesquelles
    0.43
    듬
    0.43
     اخرى
    0.43
     heartache
    0.42
     détermin
    0.42
     upto
    0.41
     determination
    0.40
    Determination
    0.40
    POSITIVE LOGITS
    rj
    0.49
    ray
    0.46
    modelLogin
    0.46
    木の
    0.45
    的な
    0.43
    ApiService
    0.43
    atedral
    0.43
    謳
    0.43
    netflix
    0.41
    島の
    0.41
    Activations Density 0.000%

    No Known Activations