© 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. 3581
    Prev
    Next
    INDEX
    Explanations

    specifying number of words or sentences

    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
     betterment
    0.63
     plenty
    0.61
     I
    0.58
     R
    0.58
    种
    0.57
    R
    0.56
     วิธี
    0.55
     creciente
    0.54
     optimum
    0.53
     我们
    0.51
    POSITIVE LOGITS
    2
    0.78
    uses
    0.71
    1
    0.71
    4
    0.70
    at
    0.67
    ла
    0.66
    se
    0.64
    itters
    0.64
    न
    0.64
    voc
    0.63
    Activations Density 0.272%

    No Known Activations