© 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. 29591
    Prev
    Next
    INDEX
    Explanations

    instructions with plans

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

    Graham Bell and mom

    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
    장
    0.53
    pá
    0.52
    па
    0.51
    δό
    0.49
    振り返
    0.47
    have
    0.47
    की
    0.47
    ḍ
    0.47
     de
    0.46
    ிர
    0.46
    POSITIVE LOGITS
     बत्रा
    0.48
     doorbell
    0.48
     সম্মিল
    0.47
     resonator
    0.46
     демонстра
    0.44
     Sieg
    0.43
     উজ্জ
    0.43
     আবেদ
    0.43
     einde
    0.42
     repeatability
    0.42
    Activations Density 0.000%

    No Known Activations