© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 5236
    Prev
    Next
    INDEX
    Explanations

    get going, build right, little bit

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

    little, a little bit

    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_31_width_262k_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
     אך
    0.57
     จึง
    0.52
     पश्चात
    0.47
    および
    0.46
    ></
    0.46
     शेष
    0.45
    จึง
    0.45
    Weitere
    0.44
     및
    0.44
     다음과
    0.44
    POSITIVE LOGITS
     ahorita
    0.80
     poquito
    0.68
     väldigt
    0.65
     people
    0.59
     veldig
    0.59
     যেটা
    0.57
    這樣子
    0.56
     cosas
    0.55
     굉장히
    0.55
     everybody
    0.55
    Activations Density 0.556%

    No Known Activations