© 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. 22463
    Prev
    Next
    INDEX
    Explanations

    infrastructure or technical details

    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
     от
    0.33
    まるで
    0.33
    neſs
    0.32
    ฺ
    0.31
    ım
    0.30
     поскольку
    0.30
    ስታ
    0.29
     зая
    0.29
    itekt
    0.29
     כאשר
    0.29
    POSITIVE LOGITS
     logits
    0.39
     phonons
    0.39
    4
    0.36
     Recursos
    0.36
    2
    0.36
     Elektrokh
    0.35
     Monographs
    0.35
    9
    0.35
    8
    0.35
     neutrophils
    0.34
    Activations Density 0.056%

    No Known Activations