© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 77427
    Prev
    Next
    INDEX
    Explanations

    congress assembled

    np_acts-logits-general · gemini-2.5-flash-lite

    haiku generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cues
    0.45
     premise
    0.45
     lineup
    0.45
     violates
    0.44
     CONSULT
    0.42
     テ
    0.41
     preconditions
    0.41
     PAR
    0.40
     highly
    0.40
     COUN
    0.39
    POSITIVE LOGITS
     erwähnt
    0.52
    சியம்
    0.48
    鲟
    0.46
     ઘણા
    0.43
    opold
    0.43
    ませんが
    0.42
     Eugène
    0.42
    相关的
    0.41
    indexBuffer
    0.40
     করলেন
    0.40
    Activations Density 0.000%

    No Known Activations