© 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. 206824
    Prev
    Next
    INDEX
    Explanations

    teaching to learn

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

    Probability Distribution

    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
    }\|^
    0.54
     रिप्रेजेंट
    0.52
     ओन
    0.51
    ྦ
    0.49
    㸸
    0.49
     बृ
    0.47
    편집
    0.47
    មិន
    0.47
    亗
    0.45
     இல்
    0.45
    POSITIVE LOGITS
     straightening
    0.47
     volatile
    0.46
     unstable
    0.45
     fem
    0.45
     of
    0.44
     chaos
    0.43
     epidemic
    0.43
     unbalanced
    0.43
     hun
    0.43
     smok
    0.43
    Activations Density 0.001%

    No Known Activations