© 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. 60125
    Prev
    Next
    INDEX
    Explanations

    superheroes behind Marvel

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

    contrasting prepositions verbs words

    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
    一
    0.51
    。\
    0.51
     京都
    0.50
     我們
    0.49
    হ
    0.47
     capitol
    0.46
     Responses
    0.45
     bloodstream
    0.45
     tx
    0.45
     都
    0.45
    POSITIVE LOGITS
     نویس
    0.50
    ்துறை
    0.47
     بھول
    0.46
     بیر
    0.46
    ifrån
    0.46
     différentes
    0.45
     پایه
    0.45
     تیز
    0.45
     ذکر
    0.44
     difícil
    0.44
    Activations Density 0.000%

    No Known Activations