© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6412
    Prev
    Next
    INDEX
    Explanations

    job boards and specific websites

    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
     caminho
    0.31
     $("<
    0.29
    प्ताह
    0.29
     emocionante
    0.28
    राबरी
    0.28
     преимущественно
    0.28
    üdis
    0.27
     melindungi
    0.27
     craindre
    0.27
     enemigos
    0.27
    POSITIVE LOGITS
    6
    0.52
    7
    0.51
    5
    0.43
    4
    0.42
    8
    0.42
    3
    0.41
    9
    0.39
    2
    0.35
    -
    0.35
    _
    0.33
    Activations Density 0.372%

    No Known Activations