© 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. 232234
    Prev
    Next
    INDEX
    Explanations

    make you understand

    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
     distribuição
    0.48
     فِي
    0.46
    鄒
    0.46
    越
    0.45
     combinação
    0.44
     консульта
    0.42
     remerc
    0.42
    越多
    0.42
    consult
    0.41
    黨
    0.41
    POSITIVE LOGITS
    ্লাম
    0.47
     ஏற்படுத்துகிறது
    0.47
    ono
    0.47
    veys
    0.45
    ίν
    0.45
     வகுப்பு
    0.45
    Connecting
    0.44
    abı
    0.44
    Theorem
    0.44
     또는
    0.44
    Activations Density 0.001%

    No Known Activations