© 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. 45582
    Prev
    Next
    INDEX
    Explanations

    stainless steel

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

    stainless steel

    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
    ﻧ
    0.45
    ﹰ
    0.43
     Subsidiary
    0.43
    કડ
    0.43
     Instructional
    0.43
     деревя
    0.43
     मधु
    0.41
     информационной
    0.41
    验
    0.41
    ゥ
    0.41
    POSITIVE LOGITS
     stainless
    0.84
     Stainless
    0.78
    Stainless
    0.77
     Edelstahl
    0.75
    stainless
    0.68
     inox
    0.66
     inoxidable
    0.63
    ステンレス
    0.63
     AISI
    0.62
     ステンレス
    0.62
    Activations Density 0.026%

    No Known Activations