© 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. 123748
    Prev
    Next
    INDEX
    Explanations

    Lost things and verification

    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
     filtra
    0.52
    ków
    0.50
    джа
    0.50
    ików
    0.50
     wynik
    0.49
    ObjData
    0.47
     項
    0.46
     secondaires
    0.46
    ке
    0.46
    кет
    0.46
    POSITIVE LOGITS
     {})
    0.47
    !!)
    0.46
    )]:
    0.41
    U
    0.40
    +)
    0.40
     【
    0.39
     REQUIRED
    0.38
     HX
    0.38
     ●
    0.38
     XVI
    0.38
    Activations Density 0.005%

    No Known Activations