© 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. 71580
    Prev
    Next
    INDEX
    Explanations

    legal dependents, stories, fry, AR, give away

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

    reachable bynote thatvacations of

    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
    概
    0.50
    謀
    0.49
    ab
    0.47
    োজন
    0.47
    庭
    0.47
     bash
    0.46
    起
    0.46
    欣
    0.45
    告
    0.45
    簡
    0.45
    POSITIVE LOGITS
     wewnętr
    0.51
     آئی
    0.50
    śl
    0.49
    लै
    0.46
     zewnętrzne
    0.46
     fluidity
    0.43
     हैज
    0.43
     warehouse
    0.43
    ässä
    0.43
     quasip
    0.42
    Activations Density 0.000%

    No Known Activations