© 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. 166441
    Prev
    Next
    INDEX
    Explanations

    types of communication

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

    Zoroastrianism, focus, safeguard

    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
    ch
    0.58
    hat
    0.57
    pf
    0.55
    v
    0.55
    is
    0.55
    u
    0.54
    ford
    0.54
    z
    0.54
    field
    0.53
    chl
    0.53
    POSITIVE LOGITS
     poważ
    0.51
     deont
    0.49
     preservar
    0.49
     disminución
    0.47
    と思って
    0.46
     zapewn
    0.46
     végétaux
    0.46
     safeguard
    0.45
     prioritization
    0.45
     pourcentage
    0.45
    Activations Density 0.000%

    No Known Activations