© 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. 164158
    Prev
    Next
    INDEX
    Explanations

    shower

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

    phi, WiFi, Bluetooth

    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
     RUN
    0.49
     에
    0.48
     enzyme
    0.46
     olid
    0.46
     ire
    0.45
     hul
    0.45
     masks
    0.45
    ਂ
    0.45
     ऑन
    0.44
     offend
    0.43
    POSITIVE LOGITS
    Phi
    0.55
    wifi
    0.53
    phi
    0.50
    Bluetooth
    0.50
    ϕ
    0.50
    WiFi
    0.48
     Tattha
    0.46
    বিভ
    0.44
    PH
    0.44
    вобо
    0.43
    Activations Density 0.000%

    No Known Activations