© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 6082
    Prev
    Next
    INDEX
    Explanations

    these [noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    에
    1.33
    に
    1.27
    ти
    1.19
    อ
    1.18
    이면
    1.15
    ется
    1.05
    ش
    1.02
    िक
    1.01
    न
    1.01
    ა
    1.01
    POSITIVE LOGITS
     وهذه
    0.82
    eek
    0.80
     amelyek
    0.76
    헙
    0.74
    ్వర
    0.73
    wolves
    0.73
    iq
    0.72
    सर्गिक
    0.72
    gul
    0.70
    ſ
    0.70
    Activations Density 0.137%

    No Known Activations