© 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. 20467
    Prev
    Next
    INDEX
    Explanations

    web links and information

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

    websites and articles

    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
    ಾನು
    0.46
    施術
    0.45
    PRIVATE
    0.44
     anodic
    0.44
     millimeter
    0.43
    𒋾
    0.43
     wysokości
    0.42
     prolet
    0.42
     diathermy
    0.42
    綁
    0.42
    POSITIVE LOGITS
     Wikipedia
    1.31
     wikipedia
    1.30
    Wikipedia
    1.16
    http
    1.02
     http
    1.02
    wikipedia
    1.01
     BBC
    0.98
     Encyclopedia
    0.96
     Wikipédia
    0.94
     websites
    0.88
    Activations Density 0.105%

    No Known Activations