© 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. 102495
    Prev
    Next
    INDEX
    Explanations

    following Will ware rings

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

    dinosaur names

    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
     расскажем
    0.51
    ουμε
    0.46
    宻
    0.46
    沍
    0.46
    鼕
    0.45
    䏼
    0.45
    䧣
    0.44
    覦
    0.44
     машиналары
    0.44
    孳
    0.44
    POSITIVE LOGITS
    wan
    0.43
     walnuts
    0.43
    w
    0.42
    ឯ
    0.42
     cleft
    0.42
    un
    0.41
    ya
    0.41
    top
    0.41
     lake
    0.40
    ung
    0.39
    Activations Density 0.001%

    No Known Activations