© 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
    5. 41-GEMMASCOPE-2-RES-262K
    7. 241469
    Prev
    Next
    INDEX
    Explanations

    PEFT

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SOME
    0.69
     ፓ
    0.59
    拃
    0.59
    rul
    0.57
    꾿
    0.56
     SOME
    0.55
    commands
    0.54
     MUCH
    0.52
    그런
    0.52
    갖
    0.51
    POSITIVE LOGITS
    在前
    0.68
     อ่า
    0.62
     amistad
    0.62
     invitados
    0.60
     dissected
    0.60
    แหน่ง
    0.60
     ersten
    0.59
     inundated
    0.59
     situated
    0.59
     overgrown
    0.58
    Activations Density 0.000%

    No Known Activations