© 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. 69231
    Prev
    Next
    INDEX
    Explanations

    phrases with 'thing', 'protected', 'being', 'chair', 'yes', 'hesitated'

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

    Analysis of situations and strategies

    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
    (
    0.52
    lov
    0.50
    loj
    0.47
    _
    0.44
    lof
    0.40
    ・
    0.40
    seed
    0.40
    )
    0.40
     Mac
    0.39
    '
    0.39
    POSITIVE LOGITS
     краё
    0.59
    घाडी
    0.55
    гали
    0.55
    гают
    0.54
     pluie
    0.52
     gemeinsamen
    0.52
     chandeliers
    0.52
    емые
    0.51
     cereals
    0.51
     पाच
    0.51
    Activations Density 0.001%

    No Known Activations