© 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. 38652
    Prev
    Next
    INDEX
    Explanations

    artist names and styles

    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
    hunters
    1.82
    ه
    1.81
    м
    1.68
    ط
    1.66
    ز
    1.65
    𝚝
    1.61
     graphique
    1.59
    ف
    1.58
    มะ
    1.56
    eers
    1.56
    POSITIVE LOGITS
     JOURNAL
    1.16
     trouser
    1.14
     tenant
    1.13
     Fun
    1.12
     Flip
    1.12
     (
    1.11
     marshmallows
    1.09
     GST
    1.09
     caz
    1.09
    不说
    1.09
    Activations Density 0.000%

    No Known Activations