© 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. 34755
    Prev
    Next
    INDEX
    Explanations

    kinds of

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

    ChatGPT, sphere, totally, mixes, bulk

    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
     새로운
    0.44
     associating
    0.44
    리에
    0.44
     ra
    0.41
     오
    0.41
    N
    0.41
     coupling
    0.40
     despised
    0.40
    因
    0.40
     swapping
    0.39
    POSITIVE LOGITS
    >"
    0.46
    вався
    0.44
    Proguard
    0.44
    Beyblade
    0.44
    Cemento
    0.43
    쏜
    0.42
    说什么
    0.42
    𒈦
    0.42
    berto
    0.42
    হইতে
    0.41
    Activations Density 0.000%

    No Known Activations