© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 28778
    Prev
    Next
    INDEX
    Explanations

    negative, German, Minister, dogs, advantages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    meed
    0.38
    agne
    0.38
    <0xB7>
    0.37
    opacity
    0.37
    uta
    0.37
    ád
    0.37
    ProtectedRoute
    0.36
    ndrome
    0.36
    sey
    0.36
     নাকি
    0.36
    POSITIVE LOGITS
     injurious
    0.45
    itriangular
    0.45
     ");
    0.44
     posibles
    0.44
     કોઈપણ
    0.44
     zawiera
    0.43
     jelent
    0.43
    冦
    0.43
     doivent
    0.43
     szybko
    0.43
    Activations Density 0.001%

    No Known Activations