© 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. 184384
    Prev
    Next
    INDEX
    Explanations

    desires no, state of

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

    analysis and explanation

    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
    t
    0.61
    音
    0.48
    ableness
    0.47
    hall
    0.46
    r
    0.46
    rl
    0.45
    ono
    0.45
    tu
    0.45
    dh
    0.45
    ?
    0.44
    POSITIVE LOGITS
     véhicules
    0.54
     عمليات
    0.53
    Gravity
    0.52
     сфере
    0.51
     operações
    0.51
     اين
    0.50
     vendeur
    0.50
     cannula
    0.50
     পরিবর্তে
    0.50
    скетбол
    0.50
    Activations Density 0.001%

    No Known Activations