© 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. 184770
    Prev
    Next
    INDEX
    Explanations

    titles and common words followed by specifics

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

    medical or technical contexts

    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
     the
    0.53
    3
    0.51
    microsoft
    0.46
     Microsoft
    0.43
     Worker
    0.43
     contraction
    0.42
    val
    0.42
     microsoft
    0.42
     t
    0.41
     McDonald
    0.41
    POSITIVE LOGITS
     времена
    0.58
     seules
    0.57
     பிரமி
    0.56
    uraea
    0.53
     seule
    0.53
     familiares
    0.51
    urr
    0.51
    ungg
    0.51
     நேரடியாக
    0.51
     seuls
    0.50
    Activations Density 0.000%

    No Known Activations