© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 85118
    Prev
    Next
    INDEX
    Explanations

    libraries and paths

    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_40_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
    pre
    0.44
     variable
    0.43
     hustle
    0.42
     낮
    0.42
    question
    0.41
     Vero
    0.41
    Ang
    0.40
     Klo
    0.39
     method
    0.39
    onać
    0.38
    POSITIVE LOGITS
     indestruct
    0.42
    textepsilon
    0.42
     पदाधिकारियों
    0.39
    }")]
    0.38
     ASGI
    0.38
     एवरीवन
    0.37
     plantations
    0.37
     convexes
    0.37
     pianta
    0.37
     MDET
    0.37
    Activations Density 0.000%

    No Known Activations