© 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. 33085
    Prev
    Next
    INDEX
    Explanations

    parenthesized phrases or alternatives

    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
    ).
    0.68
    }.
    0.62
    ].
    0.59
    %.
    0.56
     :).
    0.56
     ().
    0.56
     کی۔
    0.55
    ®.
    0.55
    .).
    0.54
    *.
    0.54
    POSITIVE LOGITS
    ？）
    0.48
     અને
    0.47
     và
    0.46
     و
    0.46
     और
    0.45
     snd
    0.45
     และ
    0.45
     आणि
    0.44
     și
    0.44
     এবং
    0.44
    Activations Density 0.107%

    No Known Activations