© 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. 112495
    Prev
    Next
    INDEX
    Explanations

    defining concepts

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

    основные направления, цели, характеристики

    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
    ieli
    0.44
     —,
    0.43
     посредством
    0.41
    angent
    0.40
    ;
    0.40
     Row
    0.40
    riche
    0.39
     μέσα
    0.39
    bea
    0.39
    through
    0.39
    POSITIVE LOGITS
    ການ
    0.49
     envío
    0.48
    რების
    0.46
     undeniable
    0.45
    SDAY
    0.45
     இருக்கிறது
    0.45
    발
    0.45
     correspondió
    0.44
     ситуации
    0.43
    적인
    0.43
    Activations Density 0.038%

    No Known Activations