© 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. 31-GEMMASCOPE-2-RES-262K
    7. 55058
    Prev
    Next
    INDEX
    Explanations

    original text explains concepts

    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
    rigues
    0.41
    Charge
    0.41
    thresh
    0.40
     giám
    0.40
    HasStarred
    0.40
    Gaming
    0.40
    TypeArguments
    0.40
    俟
    0.39
    -=
    0.38
    ഗീയ
    0.38
    POSITIVE LOGITS
     et
    0.46
    en
    0.45
    inare
    0.44
     rethink
    0.43
     recipe
    0.42
    INI
    0.42
    olo
    0.42
     Germany
    0.41
     simmering
    0.41
     probe
    0.41
    Activations Density 0.002%

    No Known Activations