© 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. 1817
    Prev
    Next
    INDEX
    Explanations

    Marques, MKBHD

    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
     scrumptious
    0.36
    嘢
    0.35
    さまざ
    0.34
    腟
    0.34
     मालूम
    0.33
    쁩
    0.33
    Toward
    0.33
     ინფორმა
    0.33
    当該
    0.33
    }^{+}\
    0.33
    POSITIVE LOGITS
    t
    0.38
     technical
    0.36
     very
    0.35
     combined
    0.35
     individual
    0.34
     fron
    0.34
     long
    0.34
     industrial
    0.33
     game
    0.33
     final
    0.32
    Activations Density 0.001%

    No Known Activations