© 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. 12454
    Prev
    Next
    INDEX
    Explanations

    how to explain or apply

    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
     socialization
    0.44
     पहला
    0.43
     Inbetriebnahme
    0.42
     preoccupation
    0.42
     tenements
    0.42
     첫
    0.41
     ersten
    0.41
     आवेद
    0.41
     erster
    0.40
     constituting
    0.40
    POSITIVE LOGITS
     інших
    0.45
    ানোর
    0.44
    న్స్
    0.44
    Otros
    0.43
    Other
    0.42
     UNDER
    0.42
    EUR
    0.42
    在
    0.41
    Others
    0.41
    在這
    0.40
    Activations Density 0.007%

    No Known Activations