© 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. 143833
    Prev
    Next
    INDEX
    Explanations

    redundant or similar

    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
     destruir
    0.50
     három
    0.49
     chloroplast
    0.49
     bốn
    0.48
     dát
    0.48
    Ⴝ
    0.47
     সমুদ্র
    0.46
     prefque
    0.45
     sucrose
    0.45
     Những
    0.45
    POSITIVE LOGITS
    ory
    0.49
     MAY
    0.49
    น
    0.48
    -
    0.47
     Entry
    0.44
    ור
    0.40
     Lynd
    0.40
    entry
    0.39
     വിശ്വാ
    0.39
    നട
    0.39
    Activations Density 0.005%

    No Known Activations