© 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. 251227
    Prev
    Next
    INDEX
    Explanations

    have for

    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
    utta
    0.46
    வா
    0.44
    arik
    0.43
    问道
    0.43
     bird
    0.43
    왑
    0.43
    瑛
    0.43
    稃
    0.43
    画布
    0.42
     pandemic
    0.42
    POSITIVE LOGITS
    posium
    0.48
     aliexpress
    0.47
    жды
    0.46
     MDL
    0.46
     existente
    0.46
     Aliexpress
    0.45
     Siam
    0.45
     ate
    0.45
    coef
    0.44
     Ate
    0.44
    Activations Density 0.000%

    No Known Activations