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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 137858
    Prev
    Next
    INDEX
    Explanations

    Department codes, chapter patterns, sensory diet

    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
    (
    0.65
    е
    0.48
    3
    0.45
    ac
    0.44
    asc
    0.44
     prev
    0.43
    。
    0.43
    รุ่น
    0.43
    esth
    0.43
    о
    0.43
    POSITIVE LOGITS
    𝘃
    0.52
    नाथन
    0.48
     psicología
    0.47
     basadas
    0.46
    ಞ
    0.46
     unsettled
    0.46
     slumped
    0.46
     휴
    0.46
    isTouching
    0.45
    lores
    0.45
    Activations Density 0.008%

    No Known Activations