© 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. 2250
    Prev
    Next
    INDEX
    Explanations

    specific criteria search

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

    Coursera and online courses

    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
    irting
    0.46
    刦
    0.42
    ष्ठा
    0.39
     колон
    0.39
    éries
    0.38
    novu
    0.38
    ন্থা
    0.38
    ocytosis
    0.37
    ঈদ
    0.37
    ച്
    0.37
    POSITIVE LOGITS
    Exact
    0.52
    Specific
    0.46
     exact
    0.45
     Exact
    0.44
    .​​
    0.43
    exact
    0.42
     classe
    0.42
    .”
    0.41
     thanks
    0.41
     courtesy
    0.41
    Activations Density 0.003%

    No Known Activations