© 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. 40-GEMMASCOPE-2-RES-262K
    7. 212796
    Prev
    Next
    INDEX
    Explanations

    examples and factual descriptions

    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
     tob
    0.38
    낙
    0.38
    yao
    0.36
    cipe
    0.36
     낙
    0.36
     ej
    0.35
    fract
    0.35
    damaged
    0.35
    wirk
    0.35
    garde
    0.35
    POSITIVE LOGITS
     pengertian
    0.47
    )}}
    0.44
    Rotate
    0.41
     pouces
    0.41
     wirklich
    0.39
    并未
    0.38
    untz
    0.38
     rotates
    0.38
     reinstated
    0.38
    立场
    0.38
    Activations Density 0.001%

    No Known Activations