© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12858
    Prev
    Next
    INDEX
    Explanations

    offering alternative content or information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    ก
    0.82
    т
    0.79
     for
    0.76
    на
    0.69
     necessary
    0.64
     on
    0.63
    е
    0.61
     furiously
    0.60
     θα
    0.59
     공급
    0.59
    POSITIVE LOGITS
    ،
    0.66
     Angebot
    0.63
     Offered
    0.59
     Gestaltung
    0.58
     muros
    0.58
    ні
    0.57
     kusal
    0.56
     proffered
    0.56
     Mön
    0.55
     konz
    0.54
    Activations Density 0.042%

    No Known Activations