© 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. 182692
    Prev
    Next
    INDEX
    Explanations

    lists and tags

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

    organizations seeking protection

    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
     Bay
    0.50
    త
    0.49
    S
    0.48
     Latin
    0.48
     Jersey
    0.46
     Decisions
    0.45
    र्त
    0.45
    ש
    0.44
    תו
    0.44
     Men
    0.44
    POSITIVE LOGITS
    warm
    0.57
     آنان
    0.57
    worms
    0.54
    antro
    0.53
     преж
    0.53
     ersche
    0.52
     incubating
    0.52
     طراحی
    0.51
     fondamentali
    0.50
     sepan
    0.50
    Activations Density 0.002%

    No Known Activations