© 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. 151046
    Prev
    Next
    INDEX
    Explanations

    something else

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

    action verbs and their followers

    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
     丶
    0.55
    MSFont
    0.46
    activo
    0.46
    oczes
    0.46
    ോക
    0.43
    اردوش
    0.43
    撳
    0.42
    atzen
    0.42
    덬
    0.42
    roud
    0.41
    POSITIVE LOGITS
     acetone
    0.47
     SPS
    0.47
    ET
    0.46
     reagents
    0.46
     guise
    0.46
     remplacement
    0.46
     equivalence
    0.44
     onto
    0.43
     whereas
    0.42
    ঢাকা
    0.42
    Activations Density 0.001%

    No Known Activations