© 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-65K
    7. 45209
    Prev
    Next
    INDEX
    Explanations

    transformers, India, pictures, placement

    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_65k_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
     —
    0.52
    煐
    0.49
     загряз
    0.44
     Goal
    0.44
     –
    0.44
    \
    0.43
     প্রতিটি
    0.43
     제공
    0.43
     목표
    0.43
     Goals
    0.42
    POSITIVE LOGITS
    ोसिएशन
    0.45
    ложении
    0.40
     Huan
    0.39
    वेदन
    0.38
    රු
    0.38
     مقام
    0.38
    स्तान
    0.37
    ா
    0.37
     epidermis
    0.36
    вес
    0.36
    Activations Density 0.001%

    No Known Activations