© 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. 15125
    Prev
    Next
    INDEX
    Explanations

    common words followed by function words

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

    identify attackers, results, describing emotions

    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
    見
    0.62
    об
    0.45
     MA
    0.43
    MA
    0.42
     Masses
    0.41
    龐
    0.41
    鳴
    0.40
    庞
    0.40
     masses
    0.40
    怎么
    0.39
    POSITIVE LOGITS
    simeq
    0.45
     encrypted
    0.44
    ത്തിലൂടെ
    0.44
    FBSDKError
    0.43
    TaskPojo
    0.43
    ުރ
    0.42
     تړ
    0.42
     hijas
    0.42
    StaticHandler
    0.41
    hse
    0.41
    Activations Density 0.000%

    No Known Activations