© 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. 70387
    Prev
    Next
    INDEX
    Explanations

    news, temperature, refrigerator, intended, dead

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

    cold hydrogen

    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
    𝕋
    0.47
    hôte
    0.47
    ası
    0.46
    기와
    0.46
     następnie
    0.46
     sırasında
    0.46
     singleArray
    0.46
    erçe
    0.45
     επί
    0.45
    encodeWith
    0.45
    POSITIVE LOGITS
     schn
    0.54
     zombies
    0.52
     importation
    0.51
     there
    0.47
     sniping
    0.47
    ?
    0.46
     pink
    0.46
     assaults
    0.45
     booze
    0.45
     people
    0.45
    Activations Density 0.000%

    No Known Activations