© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 137358
    Prev
    Next
    INDEX
    Explanations

    country, signature, or century

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

    **bold** or `controlled` followed by `*` or `Network`

    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
     रुग्
    0.50
    బీ
    0.44
     hospitals
    0.43
    养
    0.42
    తా
    0.42
    ገልግሎ
    0.41
    Melitaea
    0.41
    íduos
    0.39
    талия
    0.38
    Chars
    0.38
    POSITIVE LOGITS
    ア
    0.54
     crimson
    0.47
    𝓵
    0.47
     dono
    0.46
     ∠
    0.45
    騎士
    0.45
     inclin
    0.45
    オ
    0.45
     showdown
    0.44
     homage
    0.44
    Activations Density 0.001%

    No Known Activations