© 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. 235904
    Prev
    Next
    INDEX
    Explanations

    engineering, online, insurance, degrees

    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
    ե
    0.56
    鉅
    0.52
     harnessed
    0.51
    後的
    0.48
     घटा
    0.46
    是很
    0.45
     progressively
    0.44
     convent
    0.44
     treba
    0.44
     Schwer
    0.43
    POSITIVE LOGITS
    enal
    0.48
    outputs
    0.48
    ano
    0.48
    anku
    0.46
    ")));
    0.46
    anone
    0.45
    wood
    0.45
    "));
    0.45
    chemical
    0.45
    outdoor
    0.45
    Activations Density 0.000%

    No Known Activations