© 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. 16-GEMMASCOPE-2-RES-262K
    7. 653
    Prev
    Next
    INDEX
    Explanations

    Rishi Sunak or Marlin

    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_16_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
    anın
    0.66
     և
    0.66
    aj
    0.64
    dental
    0.64
    as
    0.63
    ும்போது
    0.62
     muslin
    0.62
    emt
    0.61
    dı
    0.60
    dru
    0.60
    POSITIVE LOGITS
    "
    0.70
    ل
    0.66
    М
    0.64
    ק
    0.64
    מ
    0.64
     proches
    0.63
    К
    0.61
    Г
    0.59
    ность
    0.58
    C
    0.58
    Activations Density 0.000%

    No Known Activations