Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 24-GEMMASCOPE-2-RES-262K
    4. 8695
    Prev
    Next
    INDEX
    Explanations

    **abstract:**

    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_24_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
    )",
    0.44
    :
    0.42
    .]
    0.42
     sop
    0.41
    .",
    0.40
    :",
    0.40
     forming
    0.40
     concealed
    0.40
    )
    0.39
    ться
    0.39
    POSITIVE LOGITS
     aveva
    0.61
     Salaries
    0.57
    जबकि
    0.57
     Beberapa
    0.55
     ขณะ
    0.54
    を担当
    0.54
     Sementara
    0.54
     керів
    0.54
    刘
    0.54
     avevano
    0.54
    Activations Density 0.047%

    No Known Activations