© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 12346
    Prev
    Next
    INDEX
    Explanations

    coming from a place

    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
    D
    0.41
    in
    0.41
    થી
    0.39
    ↵↵↵↵
    0.38
    C
    0.38
    E
    0.37
    B
    0.37
    S
    0.36
    到
    0.36
    IN
    0.35
    POSITIVE LOGITS
     afar
    0.82
     whence
    0.81
     standpoint
    0.65
     thence
    0.62
     elsewhere
    0.58
     anywhere
    0.56
     abroad
    0.54
     څخه
    0.53
     within
    0.52
     segi
    0.52
    Activations Density 0.053%

    No Known Activations