© 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. 208668
    Prev
    Next
    INDEX
    Explanations

    World War II, dog training

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

    logical states and qualities

    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
    ܣ
    0.48
    சென்னை
    0.48
    ܪ
    0.47
    čno
    0.46
    neighbour
    0.46
     također
    0.45
    מת
    0.45
    粉
    0.45
    ູ່
    0.45
    Ե
    0.44
    POSITIVE LOGITS
    ্তার
    0.44
     abstractions
    0.43
     hábitos
    0.43
     Rite
    0.43
    ahin
    0.43
    ioen
    0.43
     teller
    0.42
     Teller
    0.42
     والن
    0.42
     Cull
    0.42
    Activations Density 0.000%

    No Known Activations