© 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. 41872
    Prev
    Next
    INDEX
    Explanations

    beyond simple

    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
     charger
    0.45
     treasurer
    0.44
     care
    0.43
     conveyance
    0.43
    л
    0.43
     connecter
    0.43
     )
    0.42
     mar
    0.41
     pulses
    0.41
    )])
    0.41
    POSITIVE LOGITS
     हटा
    0.51
     Ведь
    0.51
     Krom
    0.49
    呚
    0.47
    Simplified
    0.47
    et
    0.46
     अवे
    0.46
     Renaud
    0.46
    枼
    0.46
    㳊
    0.46
    Activations Density 0.000%

    No Known Activations