© 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. 99646
    Prev
    Next
    INDEX
    Explanations

    numbers containing 5

    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
     παρα
    0.41
    Pul
    0.41
    נ
    0.41
    AY
    0.38
    ب
    0.38
     дея
    0.38
     PUL
    0.38
    筤
    0.38
     Pul
    0.38
     سوق
    0.38
    POSITIVE LOGITS
    al
    0.47
    ilien
    0.46
    ниця
    0.45
    où
    0.45
    seau
    0.44
    can
    0.44
    入り
    0.44
     tutu
    0.44
    ighe
    0.43
     পট
    0.42
    Activations Density 0.009%

    No Known Activations