© 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. 31-GEMMASCOPE-2-RES-262K
    7. 7940
    Prev
    Next
    INDEX
    Explanations

    defining descriptive terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    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
     باعث
    0.46
     важли
    0.38
     deleterious
    0.37
     કારણે
    0.37
    睍
    0.36
     Generals
    0.35
     причиной
    0.35
     leuke
    0.34
    ങ
    0.34
     murderous
    0.33
    POSITIVE LOGITS
     using
    0.59
     utilizzando
    0.53
     according
    0.52
     consisting
    0.52
     encoded
    0.51
    :<
    0.49
     identified
    0.49
     utilizando
    0.49
     USING
    0.48
     consists
    0.48
    Activations Density 0.487%

    No Known Activations