© 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. 81671
    Prev
    Next
    INDEX
    Explanations

    Superhero meanings

    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
    ジャケット
    0.52
    ና
    0.49
     платфор
    0.45
     fatig
    0.43
    гали
    0.42
    Telecom
    0.42
    などが
    0.42
     wechsel
    0.42
     kvůli
    0.41
    戝
    0.41
    POSITIVE LOGITS
     this
    0.47
    this
    0.45
     समस्याओं
    0.45
    hes
    0.44
     each
    0.44
    ümüzde
    0.43
     इस
    0.42
     सम्पूर्ण
    0.42
    ഈ
    0.42
     이러한
    0.42
    Activations Density 0.004%

    No Known Activations