© 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. 202450
    Prev
    Next
    INDEX
    Explanations

    starting new clauses or sentences

    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
     parser
    0.45
    었다
    0.44
    โ
    0.44
    intah
    0.43
     vírus
    0.43
     увеличи
    0.41
     بیچ
    0.41
     stuck
    0.41
    ূর্ত
    0.40
    Ин
    0.39
    POSITIVE LOGITS
     regrets
    0.48
    limited
    0.45
    lambda
    0.43
    nung
    0.43
     (=
    0.43
     сожа
    0.43
    attractive
    0.43
    𝒚
    0.43
     amet
    0.43
     regretted
    0.43
    Activations Density 0.002%

    No Known Activations