© 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. 35147
    Prev
    Next
    INDEX
    Explanations

    gather, discover, resourceful

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

    discourse markers and structural phrases

    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
    س
    0.54
     CIVIL
    0.50
     POLICY
    0.47
    та
    0.46
    ھی
    0.45
     RESOL
    0.45
     هی
    0.44
    促進
    0.44
    ጄ
    0.44
     Coordin
    0.44
    POSITIVE LOGITS
     博文
    0.52
    ensburg
    0.44
    apache
    0.44
    nnet
    0.44
     voltak
    0.43
     enige
    0.43
    implement
    0.42
    ethyl
    0.42
    giraffe
    0.42
    computing
    0.42
    Activations Density 0.001%

    No Known Activations