© 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. 203819
    Prev
    Next
    INDEX
    Explanations

    financial and technical terms

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

    origins or older versions

    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
     étend
    0.54
     lateribus
    0.54
    DEBUGFS
    0.52
     প্রদত্ত
    0.51
     ғ
    0.50
     graciously
    0.49
     stabilise
    0.49
     greets
    0.49
     greet
    0.49
     imediatamente
    0.48
    POSITIVE LOGITS
    Love
    0.48
    T
    0.47
    बार
    0.46
    NAM
    0.46
    ten
    0.46
    periods
    0.45
    نما
    0.44
    ்க்
    0.44
    至於
    0.44
    Tim
    0.43
    Activations Density 0.000%

    No Known Activations