© 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. 41-GEMMASCOPE-2-RES-65K
    7. 1122
    Prev
    Next
    INDEX
    Explanations

    technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_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
    ᕇ
    0.65
     EEUU
    0.63
    ׳
    0.63
    ⅙
    0.63
    ᕙ
    0.62
     ¾
    0.62
    <unused2197>
    0.62
    <unused98>
    0.61
     GDPPC
    0.59
     KEYUP
    0.59
    POSITIVE LOGITS
    <unused62>
    1.95
    <unused61>
    1.87
     whi
    1.43
     hea
    1.31
    �
    1.22
     н
    1.21
     উপজে
    1.20
    ��
    1.17
     wi
    1.13
     oth
    1.13
    Activations Density 0.247%

    No Known Activations