© 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. 49603
    Prev
    Next
    INDEX
    Explanations

    modeling positive interactions

    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
    urned
    0.49
    śród
    0.47
    一
    0.46
    া
    0.45
    ás
    0.44
    아
    0.44
    一座
    0.43
    সা
    0.43
    ´
    0.43
    an
    0.42
    POSITIVE LOGITS
     coercive
    0.49
     militaires
    0.43
     deluge
    0.43
     campagnes
    0.42
    Mock
    0.42
     wiser
    0.42
     ecosystems
    0.41
     armies
    0.40
     witty
    0.40
     grandiose
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.