© 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. 69852
    Prev
    Next
    INDEX
    Explanations

    translated to

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

    core system functions

    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
    踴
    0.47
    संस्करण
    0.46
    短短
    0.44
    implicit
    0.44
     específico
    0.44
    एन
    0.43
     seperti
    0.43
    áticas
    0.43
    ené
    0.43
    多かった
    0.42
    POSITIVE LOGITS
     반려
    0.54
     ض
    0.49
     चलकर
    0.47
     الض
    0.44
     வில
    0.43
     طلاب
    0.41
     மாண
    0.40
     쌓
    0.40
     儿童
    0.40
     몸
    0.40
    Activations Density 0.007%

    No Known Activations