© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 8560
    Prev
    Next
    INDEX
    Explanations

    when or say

    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
    да
    0.96
     l
    0.92
    ки
    0.89
    یه
    0.84
     Depression
    0.82
     DeV
    0.82
     overweight
    0.82
     გავ
    0.81
     k
    0.81
     r
    0.81
    POSITIVE LOGITS
    lardan
    1.33
    评审
    1.16
    AR
    1.12
    AS
    1.08
    ES
    1.03
    आई
    1.03
    س
    1.03
     HSPB
    1.01
    IS
    1.00
    lists
    0.98
    Activations Density 0.000%

    No Known Activations