© 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. 69798
    Prev
    Next
    INDEX
    Explanations

    company with

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

    specific entities and concepts

    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
    }.}
    0.47
    pyridazin
    0.45
    ക്കൾ
    0.45
    GONDOR
    0.45
    Ide
    0.44
    bokeh
    0.44
    र्सन
    0.43
    ुक्त
    0.43
     sól
    0.43
    thoughtId
    0.43
    POSITIVE LOGITS
    r
    0.44
     OPS
    0.44
     RT
    0.44
     দয়া
    0.44
     wirst
    0.43
     Cart
    0.43
     VERSION
    0.43
    pwd
    0.43
     Intelligent
    0.42
    钧
    0.42
    Activations Density 0.000%

    No Known Activations