© 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. 148008
    Prev
    Next
    INDEX
    Explanations

    suitability requirements

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

    inappropriate or unsuitable design

    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
    PSS
    0.46
    Herz
    0.43
    RMS
    0.41
    Nine
    0.39
    Hers
    0.39
    La
    0.39
    Portable
    0.39
    
    0.38
    Reason
    0.38
    Textbox
    0.37
    POSITIVE LOGITS
     inapplicable
    0.72
     unsuitable
    0.70
     inappropriate
    0.68
     предназна
    0.64
    适用于
    0.62
     предназначен
    0.62
     unfit
    0.58
     requires
    0.57
     unusable
    0.57
     inappropriately
    0.57
    Activations Density 0.153%

    No Known Activations