© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1290
    Prev
    Next
    INDEX
    Explanations

    equal values, lines, error

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

    file named, is less

    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
     zejména
    0.55
     szczególnie
    0.52
     нередко
    0.52
    憲
    0.52
    此事
    0.51
     حداقل
    0.51
    委員會
    0.50
     पारदर्शिता
    0.50
    贊
    0.49
    habilitation
    0.49
    POSITIVE LOGITS
     corresponds
    1.06
     equal
    1.05
     equals
    1.05
     represented
    1.03
     denoted
    0.97
     represents
    0.95
     equaling
    0.95
     correspond
    0.95
     corresponding
    0.88
     corresponded
    0.86
    Activations Density 0.198%

    No Known Activations