© 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. 19784
    Prev
    Next
    INDEX
    Explanations

    In [location],

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

    Canadian Millennials, client needs, voting machine

    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
    这家
    0.47
     omnichannel
    0.47
    Funding
    0.43
     cavité
    0.43
    铄
    0.42
    璋
    0.42
    这款
    0.41
    濵
    0.41
     bistro
    0.40
     ہے
    0.40
    POSITIVE LOGITS
     Campeonato
    0.50
     तसेच
    0.47
    এবং
    0.47
    id
    0.46
     এবং
    0.45
     наоборот
    0.44
     sowie
    0.43
     সর্বপ্রথম
    0.43
     El
    0.42
     N
    0.42
    Activations Density 0.000%

    No Known Activations