© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 127570
    Prev
    Next
    INDEX
    Explanations

    conditional recommendation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     в
    0.53
     попасть
    0.52
    produktion
    0.51
     d
    0.51
     за
    0.50
     спря
    0.50
    ulier
    0.49
     إلى
    0.49
     Fluids
    0.48
    𝘆
    0.48
    POSITIVE LOGITS
     Institutional
    0.47
    '");
    0.46
     Litt
    0.45
     institutional
    0.45
    mce
    0.44
     fréquent
    0.43
    ினான்
    0.43
    Minister
    0.41
    ক্ষেপ
    0.40
    ندوق
    0.40
    Activations Density 0.002%

    No Known Activations