© 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. 2219
    Prev
    Next
    INDEX
    Explanations

    mobilegeddon and devices

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

    compatibility and influence

    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
    匏
    0.45
    liono
    0.42
    als
    0.40
    fillStyle
    0.40
     داری
    0.40
     Smithsonian
    0.39
    ension
    0.39
    لون
    0.39
    TextArea
    0.39
     જેમાં
    0.39
    POSITIVE LOGITS
     synapse
    0.46
    🚅
    0.45
     uncommon
    0.45
    WEEK
    0.43
     insomnia
    0.43
     Leuven
    0.43
    نوات
    0.42
     GDPR
    0.42
     sockfd
    0.42
     fraudsters
    0.42
    Activations Density 0.000%

    No Known Activations