© 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. 71479
    Prev
    Next
    INDEX
    Explanations

    robustness and stability

    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
     разнообраз
    0.46
     Umgang
    0.45
    龊
    0.44
    ಪಟ್ಟ
    0.44
    㛣
    0.44
    玠
    0.43
    ன்பது
    0.43
    夰
    0.43
     разно
    0.43
    PatientR
    0.43
    POSITIVE LOGITS
     mech
    0.54
    centage
    0.47
    cell
    0.47
     mobilization
    0.47
     jute
    0.44
    生ま
    0.43
     humus
    0.43
     ചേർ
    0.42
     ozone
    0.41
     forging
    0.41
    Activations Density 0.009%

    No Known Activations