© 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. 107171
    Prev
    Next
    INDEX
    Explanations

    since the

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

    finite mathematical 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
    бри
    0.48
    Ա
    0.46
    Landscape
    0.45
    병
    0.45
    ाग्राम
    0.45
    Archives
    0.45
    ДУ
    0.44
    볍
    0.44
    UT
    0.43
    भू
    0.43
    POSITIVE LOGITS
     billionaires
    0.55
     thermodynamic
    0.53
     nonempty
    0.52
     denominator
    0.51
     diameters
    0.50
    ដែល
    0.49
     universe
    0.49
     ransomware
    0.49
     bosonic
    0.49
     eigenvalues
    0.48
    Activations Density 0.000%

    No Known Activations