© 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. 54186
    Prev
    Next
    INDEX
    Explanations

    have come or consulate in

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

    softened angles blurred

    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
    我认为
    0.45
    তাহাকে
    0.44
    𝐱
    0.42
    сын
    0.41
    ثت
    0.40
     tetanus
    0.40
    proposed
    0.39
    zustellen
    0.38
    diabetes
    0.38
     Conductivity
    0.38
    POSITIVE LOGITS
    スマート
    0.49
    市場
    0.46
     elegante
    0.45
     limitado
    0.44
     '';
    0.43
     escena
    0.42
     burb
    0.41
     informazioni
    0.41
    anda
    0.40
     सितारों
    0.40
    Activations Density 0.000%

    No Known Activations