© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 77686
    Prev
    Next
    INDEX
    Explanations

    highlights or emphasizes

    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
     Geç
    0.48
     Département
    0.47
    কিছু
    0.46
     Fears
    0.45
    铯
    0.45
     Simeon
    0.45
     creencias
    0.44
    <unused2127>
    0.44
     Álvaro
    0.44
     بالإضافة
    0.43
    POSITIVE LOGITS
     from
    0.52
    from
    0.50
    endl
    0.47
     pairs
    0.43
     landscaped
    0.42
     vert
    0.41
     photosynthetic
    0.41
     thru
    0.41
     verticals
    0.41
     contribution
    0.40
    Activations Density 0.025%

    No Known Activations