© 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. 137084
    Prev
    Next
    INDEX
    Explanations

    g id or transform

    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
    illo
    0.39
    広い
    0.36
    "],[
    0.36
    arrest
    0.36
    ersiz
    0.35
    ](./
    0.35
    切
    0.35
     bề
    0.34
     transit
    0.34
     medium
    0.34
    POSITIVE LOGITS
     hunt
    0.47
     hunts
    0.47
     plunder
    0.43
     مؤ
    0.42
    ្ប
    0.42
     youngsters
    0.41
     joven
    0.40
     alkaloids
    0.40
     kalk
    0.38
     youngster
    0.38
    Activations Density 0.001%

    No Known Activations