© 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. 187873
    Prev
    Next
    INDEX
    Explanations

    request notification

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

    revenue, potential, changes

    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
    n
    0.58
    a
    0.57
    strel
    0.52
    ఆర్
    0.52
    stven
    0.51
     televisie
    0.50
     தோட்ட
    0.49
     previo
    0.48
    []');
    0.47
    iš
    0.47
    POSITIVE LOGITS
     LIGHT
    0.49
     Transmitter
    0.45
     Specimens
    0.44
     Transactions
    0.44
     Chassis
    0.44
     compass
    0.44
    意思是
    0.44
     Correlations
    0.43
     Light
    0.43
     vibration
    0.43
    Activations Density 0.001%

    No Known Activations