© 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. 4627
    Prev
    Next
    INDEX
    Explanations

    counting or quantity of items

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

    quantity per unit

    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
     seperti
    0.22
     açısından
    0.21
    ുകയാണ്
    0.21
     थोड़ा
    0.20
    𒌦
    0.20
     hep
    0.20
     tabii
    0.20
     sosok
    0.20
     fü
    0.20
     hapless
    0.19
    POSITIVE LOGITS
     apiece
    0.42
    씩
    0.31
     подряд
    0.29
     consecutivos
    0.28
     плюс
    0.27
     максимум
    0.26
    以上的
    0.26
    一共
    0.26
    合計
    0.26
     each
    0.25
    Activations Density 0.517%

    No Known Activations