© 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. 158752
    Prev
    Next
    INDEX
    Explanations

    industry specific, your experience, Microwave fruit, provides ministry

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

    Requirements, verdict, mail, what if

    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
    m
    0.49
    ९
    0.45
    walking
    0.44
    м
    0.44
     сал
    0.43
    p
    0.43
    𝐫
    0.43
    的过程中
    0.42
    띠
    0.42
     велосипе
    0.41
    POSITIVE LOGITS
    TIME
    0.48
     olig
    0.48
     outcry
    0.46
    percayaan
    0.45
     oceans
    0.45
     alkali
    0.43
     oce
    0.43
    ᒥ
    0.43
     uproar
    0.43
     eine
    0.43
    Activations Density 0.001%

    No Known Activations