© 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. 7981
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    }$.
    1.29
    。
    1.28
    식회사
    1.23
     brainchild
    1.20
    }$,
    1.16
    া
    1.16
    ।
    1.13
     brisket
    1.08
    ).}
    1.07
     cocker
    1.06
    POSITIVE LOGITS
    د
    1.59
    le
    1.49
    gü
    1.38
    ע
    1.33
    ifié
    1.32
    Face
    1.25
    ssä
    1.22
    पिछले
    1.20
    də
    1.20
    м
    1.20
    Activations Density 0.418%

    No Known Activations