© 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. 200605
    Prev
    Next
    INDEX
    Explanations

    authorization, specifications, perceived

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

    career success, investigated changes, starts with

    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
     pleinement
    0.49
    塬
    0.45
    其中的
    0.45
     مبلغ
    0.43
    上述
    0.42
    Recommended
    0.42
    充分
    0.41
     FJ
    0.40
    具备
    0.40
     المملكة
    0.40
    POSITIVE LOGITS
     zve
    0.56
     controls
    0.55
     ಖ
    0.53
     assaults
    0.53
     criminality
    0.49
     circling
    0.49
     setups
    0.49
     イ
    0.49
    rž
    0.48
     insults
    0.48
    Activations Density 0.000%

    No Known Activations