© 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. 224708
    Prev
    Next
    INDEX
    Explanations

    specific words and clauses following them

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

    analogies with specific objects

    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
    dS
    0.54
    p
    0.48
     заро
    0.47
    k
    0.46
    гур
    0.46
    dN
    0.45
     salwar
    0.45
    ुर
    0.44
    dq
    0.43
    anneled
    0.43
    POSITIVE LOGITS
    逭
    0.55
     engage
    0.50
     স্থানের
    0.49
     unlucky
    0.49
    వంటి
    0.48
    INDE
    0.48
     instruct
    0.47
     Há
    0.47
     الأمر
    0.47
    তিনি
    0.46
    Activations Density 0.001%

    No Known Activations