© 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-65K
    7. 49881
    Prev
    Next
    INDEX
    Explanations

    . board representations

    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
     ยาว
    0.44
    ^{*}=
    0.44
    暗示
    0.43
     euphoria
    0.41
     индекс
    0.41
    㩽
    0.41
    谔
    0.40
    拇
    0.39
     incompetence
    0.38
    踌
    0.38
    POSITIVE LOGITS
     restaurant
    0.46
    Restaurant
    0.41
    Pick
    0.41
     community
    0.40
     workshop
    0.40
    э
    0.39
     between
    0.39
     pay
    0.38
     wants
    0.38
     cloud
    0.38
    Activations Density 0.007%

    No Known Activations