© 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. 101388
    Prev
    Next
    INDEX
    Explanations

    looking for information

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

    tokens after special characters

    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
    اشی
    0.53
     adsor
    0.43
     agres
    0.42
    ふ
    0.42
    الی
    0.42
     inesper
    0.42
    ગ્ર
    0.42
     φ
    0.42
     indignation
    0.41
    anyo
    0.41
    POSITIVE LOGITS
    Toronto
    0.48
     जिन्होंने
    0.45
    Balt
    0.45
    珠
    0.45
     Voilà
    0.44
    Virat
    0.44
     možné
    0.43
    了嗎
    0.43
     Når
    0.43
    ochet
    0.43
    Activations Density 0.001%

    No Known Activations