© 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. 31-GEMMASCOPE-2-RES-65K
    7. 20697
    Prev
    Next
    INDEX
    Explanations

    cost, better, worth

    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_31_width_65k_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
    5
    0.43
     Dieses
    0.39
    3
    0.38
    ib
    0.37
    7
    0.37
     này
    0.36
     Here
    0.35
     ৭
    0.35
     확보
    0.34
    ଂ
    0.34
    POSITIVE LOGITS
     kwenye
    0.55
     στη
    0.50
     στον
    0.50
     στην
    0.49
     của
    0.46
    នៃ
    0.45
    咶
    0.45
    ใช้งาน
    0.44
    <unused2199>
    0.44
    𒌨
    0.43
    Activations Density 0.474%

    No Known Activations