© 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. 37835
    Prev
    Next
    INDEX
    Explanations

    emergency, car seat, sizes

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

    depending on

    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
     tuvo
    0.52
     είχε
    0.48
     didn
    0.42
    沒
    0.41
    ية
    0.40
     didnt
    0.40
     counsellor
    0.40
     wrongfully
    0.39
     не
    0.39
     tuvieron
    0.39
    POSITIVE LOGITS
    testid
    0.45
    嗉
    0.45
     Historia
    0.44
    gegeben
    0.44
     Überblick
    0.44
    kern
    0.43
    ar
    0.42
    fär
    0.42
     Länge
    0.42
     প্রজাতির
    0.42
    Activations Density 0.000%

    No Known Activations