© 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. 31-GEMMASCOPE-2-RES-262K
    7. 189446
    Prev
    Next
    INDEX
    Explanations

    A to Z Challenge

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

    specific keywords followed by colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    hampton
    0.48
    -
    0.48
    domestic
    0.47
    dem
    0.46
    transport
    0.46
    kis
    0.46
     congen
    0.45
    person
    0.45
    Alexis
    0.45
    lived
    0.44
    POSITIVE LOGITS
     वेगवेग
    0.53
     Asset
    0.52
     Segment
    0.52
     Datei
    0.52
    瑪
    0.51
     Readable
    0.50
     Feelings
    0.50
     брау
    0.50
     Populate
    0.50
     ஸ்மார
    0.50
    Activations Density 0.001%

    No Known Activations