© 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. 68300
    Prev
    Next
    INDEX
    Explanations

    full spectrum, fake fire

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

    Key words and phrases in lists

    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
    łości
    0.42
    IVAL
    0.39
    이었다
    0.39
    𝔼
    0.38
    клады
    0.38
     했던
    0.38
    ADELPHIA
    0.38
    .\\
    0.37
     μεγά
    0.37
     മാത്രം
    0.36
    POSITIVE LOGITS
     ۽
    0.47
    そして
    0.46
     ਅਤੇ
    0.44
     ແລະ
    0.44
     그리고
    0.41
    ですし
    0.40
     และ
    0.40
     anda
    0.40
     Gives
    0.39
     និង
    0.39
    Activations Density 0.041%

    No Known Activations