© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 8501
    Prev
    Next
    INDEX
    Explanations

    HTML tags and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     хірур
    0.48
    ᒥ
    0.47
    alignat
    0.46
     expts
    0.45
    𝗋
    0.45
     eqn
    0.45
    𝔂
    0.45
     exothermic
    0.45
     wavefunction
    0.43
    ହି
    0.42
    POSITIVE LOGITS
     movies
    0.54
     Movies
    0.50
     movie
    0.44
     films
    0.44
     Edith
    0.44
    Movies
    0.44
    movies
    0.44
     main
    0.43
     El
    0.43
    0.43
    Activations Density 0.000%

    No Known Activations