© 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-65K
    7. 45285
    Prev
    Next
    INDEX
    Explanations

    common phrases and specific contexts

    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_65k_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
    ative
    0.43
    igen
    0.42
     and
    0.42
    <0x0D>
    0.41
     approaches
    0.41
    Neue
    0.40
    
    0.40
    arian
    0.40
    chn
    0.40
    reated
    0.40
    POSITIVE LOGITS
     tetapi
    0.49
    퐫
    0.46
    けれ
    0.45
     putem
    0.44
     ولكن
    0.43
     throwIfNotFound
    0.43
     opět
    0.43
     usługi
    0.42
    浯
    0.42
     verantwort
    0.42
    Activations Density 0.016%

    No Known Activations