© 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-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201363
    Prev
    Next
    INDEX
    Explanations

    Here's the explanation for the neuron's behavior:non-consensual act

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_width_262k_l0_small_affine
    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
    {}
    0.42
    线性
    0.38
    線性
    0.38
    ån
    0.36
    appear
    0.36
     despe
    0.36
    linear
    0.36
     परि
    0.35
    Linear
    0.35
    put
    0.35
    POSITIVE LOGITS
     notificações
    0.41
    ೂರಿನ
    0.40
     Oste
    0.39
     Besucher
    0.38
     ایکس
    0.38
    वालियर
    0.38
     motivates
    0.37
     connects
    0.37
    젬
    0.37
     stirs
    0.37
    Activations Density 0.005%

    No Known Activations