© 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. 22436
    Prev
    Next
    INDEX
    Explanations

    flora and fauna diversity

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

    flora and fauna variety

    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
     informée
    0.55
    ясплат
    0.54
    রাষ্ট্রম
    0.48
    সম্পাদকীয়
    0.48
    সঙ্গত
    0.48
     প্রতিশোধ
    0.47
     शहरों
    0.47
    谶
    0.47
    트워크
    0.47
    特朗普
    0.47
    POSITIVE LOGITS
     flora
    0.89
     fauna
    0.86
     rare
    0.85
     rarer
    0.68
     invertebrates
    0.67
     rarest
    0.67
     abundance
    0.66
     abundant
    0.64
     endemic
    0.64
     species
    0.62
    Activations Density 0.086%

    No Known Activations