© 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. 3890
    Prev
    Next
    INDEX
    Explanations

    creative studio names

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

    Python code execution

    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
    ır
    0.41
    iré
    0.40
    ắt
    0.38
    anges
    0.38
    iction
    0.38
    疮
    0.38
    wie
    0.37
    bff
    0.37
    痛
    0.37
    abolism
    0.37
    POSITIVE LOGITS
     bernama
    0.44
     국내
    0.43
     numerosi
    0.42
     numele
    0.42
    カメラ
    0.42
     aquel
    0.42
    在国内
    0.41
     bilangan
    0.41
     pasukan
    0.41
     EMU
    0.41
    Activations Density 0.000%

    No Known Activations