© 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. 109818
    Prev
    Next
    INDEX
    Explanations

    every launch, many Arab

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

    authentication, tokens, or code

    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
    Дан
    0.51
    сная
    0.51
    !\!\
    0.51
    برای
    0.50
    ienti
    0.50
    み
    0.49
    さ
    0.49
     Stereo
    0.48
    ீ
    0.48
    し
    0.47
    POSITIVE LOGITS
     escalate
    0.48
     денег
    0.46
     turtleneck
    0.45
     provoke
    0.44
     maven
    0.44
     upheld
    0.43
     posthum
    0.43
    alja
    0.43
     kle
    0.43
     consom
    0.42
    Activations Density 0.000%

    No Known Activations