© 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. 204329
    Prev
    Next
    INDEX
    Explanations

    exponent division

    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
    "><?=$
    0.43
    ']=$
    0.42
    தி
    0.41
     nucleotide
    0.41
     Immaculate
    0.40
    }=$
    0.40
     className
    0.38
    ፀ
    0.38
     ক্যারি
    0.37
     ninguno
    0.37
    POSITIVE LOGITS
    чина
    0.39
    Edu
    0.36
    LO
    0.35
    concept
    0.35
    basan
    0.35
    ଲା
    0.34
    Walt
    0.34
    ทรวง
    0.34
    Neder
    0.33
    slant
    0.33
    Activations Density 0.000%

    No Known Activations