© 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. 113237
    Prev
    Next
    INDEX
    Explanations

    new additions and responsibility

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

    programming tools and collaboration

    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
     krwi
    0.45
     Sensors
    0.44
     komplik
    0.44
     motions
    0.43
     Dhabi
    0.43
     assimil
    0.42
     ሚ
    0.42
     액
    0.42
     Sensor
    0.42
     sensors
    0.41
    POSITIVE LOGITS
    a
    0.45
    γν
    0.43
    так
    0.42
    㐰
    0.41
    AddItem
    0.41
     furnishes
    0.40
     FURN
    0.40
    悳
    0.40
    ごろ
    0.40
     arac
    0.39
    Activations Density 0.001%

    No Known Activations