© 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. 49909
    Prev
    Next
    INDEX
    Explanations

    price, represented, count

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

    halved lengthwise

    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
    インタ
    0.43
    habitat
    0.43
    elapse
    0.42
    ﻨ
    0.42
    Norway
    0.42
    PGC
    0.41
    electrolyte
    0.41
     Norway
    0.40
    maras
    0.40
    housing
    0.40
    POSITIVE LOGITS
     سعر
    0.51
     totalPrice
    0.48
    가격
    0.48
     车
    0.47
     wrestle
    0.47
    ртка
    0.47
     beerCount
    0.46
    جع
    0.45
     svou
    0.45
    lineEdit
    0.45
    Activations Density 0.000%

    No Known Activations