© 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. 197089
    Prev
    Next
    INDEX
    Explanations

    describing their

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

    Friendly tree leaves gently

    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
    Как
    0.48
    Seperti
    0.45
    Desde
    0.44
    Mientras
    0.44
    satisf
    0.44
    Como
    0.44
    ⏎
    0.43
    こだ
    0.43
    पहले
    0.43
    Pclass
    0.43
    POSITIVE LOGITS
    വുമായി
    0.47
    ছিল
    0.47
     upsetting
    0.46
     skateboarding
    0.46
     Blackboard
    0.46
    ův
    0.44
    ун
    0.44
     described
    0.43
     simulated
    0.43
     culturally
    0.43
    Activations Density 0.000%

    No Known Activations