© 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. 156061
    Prev
    Next
    INDEX
    Explanations

    employer clinics

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

    breakdown of information

    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
    "
    0.47
    '
    0.45
    *((
    0.44
    arek
    0.42
    }+(\
    0.41
    *\*
    0.41
    attle
    0.40
    ärten
    0.40
    (
    0.40
    /
    0.40
    POSITIVE LOGITS
    Kiza
    0.53
    ሒ
    0.52
     উদ্বাস্ত
    0.48
     columnspan
    0.47
    KSpriteNode
    0.47
     nervously
    0.46
     অবজারভার
    0.46
     компен
    0.46
    hnen
    0.46
     আমেরিকান
    0.45
    Activations Density 0.000%

    No Known Activations