© 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. 7193
    Prev
    Next
    INDEX
    Explanations

    this entry was posted

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

    explain the meaning

    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
     piccoli
    0.50
     Vorsch
    0.46
     Laufe
    0.46
    sensitivity
    0.45
    ichting
    0.45
     kleiner
    0.44
     Ð
    0.44
     Aussch
    0.44
     Schule
    0.44
     Auff
    0.43
    POSITIVE LOGITS
    惮
    0.52
    രുവന
    0.50
     pénétr
    0.49
    𝔪
    0.49
    ంలో
    0.48
     обязан
    0.47
     disqual
    0.47
     देणे
    0.46
     दिर
    0.46
     arrêter
    0.46
    Activations Density 0.000%

    No Known Activations