© 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. 32960
    Prev
    Next
    INDEX
    Explanations

    articles followed by words

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

    For a long time

    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
     серде
    0.49
    ке
    0.48
    ė
    0.48
    texas
    0.46
     sensi
    0.46
    ç
    0.46
    牵
    0.45
     вмеша
    0.45
     especial
    0.45
    ?-
    0.45
    POSITIVE LOGITS
     rigidity
    0.47
    ግር
    0.45
     officiel
    0.45
     যতই
    0.43
    thorpe
    0.42
    তুম
    0.41
    Decimal
    0.40
     decimals
    0.40
     officielles
    0.40
     যদিও
    0.40
    Activations Density 0.008%

    No Known Activations