© 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. 180927
    Prev
    Next
    INDEX
    Explanations

    like this

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

    learns to map inputs to outputs

    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
     cover
    0.47
     fore
    0.46
    edit
    0.46
     ghe
    0.45
    ↵↵
    0.45
     guard
    0.45
     inter
    0.44
     tragedy
    0.44
     tragic
    0.44
     guards
    0.44
    POSITIVE LOGITS
    ᱘
    0.49
    农民
    0.48
    దవ
    0.48
     pią
    0.47
     पुश
    0.47
    機能を
    0.47
     অবস্থানে
    0.46
     бк
    0.46
    がいる
    0.46
    ড়
    0.45
    Activations Density 0.001%

    No Known Activations