© 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. 64317
    Prev
    Next
    INDEX
    Explanations

    to run

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

    adaptability, popular, understanding, short

    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
    ன்ன
    0.49
     информации
    0.48
    تها
    0.47
    ம்மா
    0.47
     información
    0.47
     сооб
    0.46
     Роман
    0.45
    ј
    0.45
    arr
    0.45
    elligence
    0.45
    POSITIVE LOGITS
     FA
    0.52
     powertrain
    0.44
     กํา
    0.44
    AGMENT
    0.44
     ऑन
    0.43
    YP
    0.43
     przyję
    0.42
     sportswear
    0.42
    opolymer
    0.42
    図柄
    0.42
    Activations Density 0.000%

    No Known Activations