© 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. 78582
    Prev
    Next
    INDEX
    Explanations

    explaining the preceding text

    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
     indicative
    0.47
    는
    0.46
     redo
    0.46
     virtual
    0.44
     backlog
    0.43
     revolution
    0.43
     tren
    0.41
     be
    0.41
     trend
    0.39
     advantage
    0.39
    POSITIVE LOGITS
     cafeter
    0.49
    apatt
    0.48
     podían
    0.48
    नपुर
    0.47
    <unused2179>
    0.47
     između
    0.46
    ारात
    0.46
    𝓪
    0.46
     Хотя
    0.46
     خودم
    0.46
    Activations Density 0.010%

    No Known Activations