© 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. 122081
    Prev
    Next
    INDEX
    Explanations

    academic and technical information

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

    handles input and subscriber information

    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
     zwar
    0.56
     معنى
    0.55
     знаете
    0.51
    代价
    0.49
    ти
    0.49
     zwart
    0.48
     そこ
    0.47
    悖
    0.47
     werde
    0.47
    förm
    0.47
    POSITIVE LOGITS
    லில்
    0.47
     ELEMENT
    0.47
    CONTAIN
    0.46
     LOGIN
    0.46
    DEC
    0.44
    BOAT
    0.44
     TOWN
    0.44
    Acknowledgement
    0.44
     basic
    0.43
     BASIC
    0.43
    Activations Density 0.001%

    No Known Activations