© 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. 4209
    Prev
    Next
    INDEX
    Explanations

    alternative followed by a noun

    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
    อ
    1.78
    有很多
    1.75
    쐞
    1.68
     axe
    1.59
    ワ
    1.59
     montrer
    1.58
    り
    1.56
    Lovely
    1.55
    Noeud
    1.55
    ه
    1.52
    POSITIVE LOGITS
    us
    2.13
     tatsächlich
    1.81
    en
    1.80
    ion
    1.78
     rozpoczę
    1.77
     ước
    1.73
     serupa
    1.69
     estrellas
    1.66
     זאת
    1.66
     의해
    1.60
    Activations Density 0.013%

    No Known Activations