© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 527
    Prev
    Next
    INDEX
    Explanations

    taken to the streets

    np_acts-logits-general · gemini-2.5-flash-lite

    establish or break precedents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     بالش
    0.24
     usando
    0.24
    Anything
    0.24
     screwing
    0.24
     Anything
    0.24
    蓣
    0.23
     USING
    0.23
    諧
    0.22
     গণনা
    0.22
     zb
    0.22
    POSITIVE LOGITS
     precedent
    0.34
     precedence
    0.32
     refuge
    0.32
     solace
    0.32
     precedents
    0.32
    heartedly
    0.31
     metaphorical
    0.31
     dib
    0.31
     traction
    0.31
     grud
    0.31
    Activations Density 0.643%

    No Known Activations