© 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. 112305
    Prev
    Next
    INDEX
    Explanations

    trouble, happened, tent, Saucers, control, engineering, hence

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

    facial expressions, animation, economic

    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
    淩
    0.40
    蔓
    0.39
    мо
    0.38
     ಬಳ
    0.38
    HILL
    0.37
    у
    0.36
    霈
    0.36
    panion
    0.36
     መሳሪያ
    0.36
    ो
    0.36
    POSITIVE LOGITS
     inclusiv
    0.47
     obstru
    0.46
     variación
    0.45
     vemos
    0.45
     conson
    0.45
     ictal
    0.44
     ulteriori
    0.43
    বাদের
    0.43
     konkret
    0.43
     oración
    0.43
    Activations Density 0.001%

    No Known Activations