© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 105198
    Prev
    Next
    INDEX
    Explanations

    welcome to the forum

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

    intensified descriptions

    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
    ISP
    0.53
    洙
    0.49
    de
    0.48
     Configuration
    0.47
    Vý
    0.47
    CUSTOM
    0.45
    USP
    0.44
    İ
    0.44
    從
    0.43
    width
    0.43
    POSITIVE LOGITS
     devast
    0.49
     ແລະ
    0.48
    んでも
    0.48
    անակ
    0.48
     portent
    0.47
    никам
    0.47
     irreparable
    0.46
    iphat
    0.46
     dysfunctional
    0.46
     contabil
    0.46
    Activations Density 0.000%

    No Known Activations