© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9339
    Prev
    Next
    INDEX
    Explanations

    contacting for information or details

    np_acts-logits-general · gemini-2.5-flash-lite

    in the

    np_acts-logits-general · gemini-2.5-flash-lite

    contact information

    np_max-act-logits · claude-4-5-sonnetTriggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ক্যারিয়ার
    0.50
     FAX
    0.47
     Fax
    0.45
    Fax
    0.45
     headquarters
    0.44
     \$
    0.44
     পরিষে
    0.44
     संपर्क
    0.43
    䐪
    0.43
     Headquarters
    0.43
    POSITIVE LOGITS
     details
    0.57
     informally
    0.56
    queries
    0.53
    details
    0.53
     summar
    0.52
    Details
    0.50
     informal
    0.50
     relevant
    0.50
    рган
    0.48
     queries
    0.48
    Activations Density 0.194%

    No Known Activations