© 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. 31027
    Prev
    Next
    INDEX
    Explanations

    equal to

    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
    意思是
    1.32
    కు
    1.31
    sld
    1.20
    ił
    1.16
    лно
    1.15
    َ
    1.14
    /-}$
    1.13
    ນ
    1.13
     climático
    1.11
    aient
    1.10
    POSITIVE LOGITS
    ি
    1.67
    았
    1.44
    ן
    1.41
    로운
    1.37
    았다
    1.36
    ated
    1.29
    ো
    1.28
    ă
    1.28
    ている
    1.23
     частина
    1.22
    Activations Density 0.002%

    No Known Activations