© 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. 143888
    Prev
    Next
    INDEX
    Explanations

    ventilation, AI capabilities

    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
     こんにちは
    0.49
     laughs
    0.47
     Nghi
    0.47
     zgodnie
    0.47
    ‏:‏
    0.47
     röm
    0.47
     questa
    0.46
    굼
    0.46
     Acest
    0.45
     redshifts
    0.45
    POSITIVE LOGITS
    etric
    0.48
    o
    0.48
    bo
    0.46
    oxy
    0.45
    ale
    0.45
    boy
    0.45
    col
    0.45
    sel
    0.44
     Boy
    0.44
     moderate
    0.44
    Activations Density 0.002%

    No Known Activations