© 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. 146093
    Prev
    Next
    INDEX
    Explanations

    detectors, remember, food, concepts

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

    extremely dangerous flammable materials

    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
     procured
    0.52
    rc
    0.46
     procurement
    0.46
    j
    0.46
     sampling
    0.46
     villages
    0.46
     organisms
    0.46
     downloading
    0.46
     on
    0.45
     before
    0.44
    POSITIVE LOGITS
    佷
    0.53
     тео
    0.51
    wość
    0.51
     фундамента
    0.51
    ższy
    0.49
     Mandalorian
    0.48
    🧱
    0.48
    trashItem
    0.48
    Mât
    0.48
    瓴
    0.48
    Activations Density 0.001%

    No Known Activations