© 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. 239009
    Prev
    Next
    INDEX
    Explanations

    checking, review, further information

    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
    紆
    0.51
     enthal
    0.49
    新年
    0.49
    出産
    0.45
     tenis
    0.45
    lift
    0.44
    ри
    0.44
     टेनिस
    0.43
    ळख
    0.43
     niños
    0.42
    POSITIVE LOGITS
     Circuits
    0.47
     વ્યવ
    0.46
    のかもし
    0.45
    、​
    0.45
    适配
    0.45
     Masks
    0.45
    enschutz
    0.44
     Interfaces
    0.43
     Motors
    0.43
    MASK
    0.43
    Activations Density 0.000%

    No Known Activations