© 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. 6918
    Prev
    Next
    INDEX
    Explanations

    scleroderma or Fantastic Four

    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
    k
    0.93
    g
    0.86
    O
    0.86
    OP
    0.81
    UR
    0.79
    OU
    0.75
    OW
    0.74
     It
    0.74
    UM
    0.74
    j
    0.73
    POSITIVE LOGITS
     elenc
    0.67
     on
    0.66
     by
    0.65
    нома
    0.65
     eluted
    0.65
     pronunciation
    0.62
     el
    0.62
     painfully
    0.61
    ни
    0.60
     compulsive
    0.59
    Activations Density 0.001%

    No Known Activations