© 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. 136049
    Prev
    Next
    INDEX
    Explanations

    option trade

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

    facts, characteristics, ideas

    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
    WAY
    0.48
     ecclesiastical
    0.46
     eyepiece
    0.46
     techniques
    0.45
     Gospel
    0.45
     to
    0.44
    .=
    0.44
     eccles
    0.44
     recou
    0.43
     entreten
    0.43
    POSITIVE LOGITS
    ླ
    0.46
    شوند
    0.45
    мі
    0.44
    ద్దా
    0.42
    ారి
    0.41
    莧
    0.41
     സമര
    0.41
    स्तान
    0.41
    rival
    0.41
    支援
    0.41
    Activations Density 0.000%

    No Known Activations