© 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. 151012
    Prev
    Next
    INDEX
    Explanations

    conjectured, hypotheses, speculation

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

    mathematical conjectures

    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
    fot
    0.54
    DELAY
    0.53
    convén
    0.52
    delay
    0.49
    fahren
    0.49
    Ｘ
    0.48
    chond
    0.48
    porte
    0.48
    dirty
    0.48
    豚
    0.47
    POSITIVE LOGITS
     estate
    0.51
     speculation
    0.51
     conjectures
    0.51
     aspirations
    0.50
     conjectured
    0.48
     believers
    0.48
     prospectus
    0.48
     hopes
    0.48
     games
    0.47
     somente
    0.47
    Activations Density 0.001%

    No Known Activations