© 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. 5130
    Prev
    Next
    INDEX
    Explanations

    nothing like

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

    bio-organic investigation

    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
    EN
    0.53
     gestern
    0.50
    Ꮑ
    0.48
    brahim
    0.47
     pued
    0.46
    decimals
    0.46
    mons
    0.46
    remember
    0.46
     consumes
    0.45
    kelig
    0.45
    POSITIVE LOGITS
     bureaucratic
    0.54
     સ્ક
    0.48
     motorway
    0.48
    י
    0.45
    ียน
    0.44
     २०२
    0.43
     dimerization
    0.43
     sighting
    0.43
    มากขึ้น
    0.42
    くん
    0.42
    Activations Density 0.000%

    No Known Activations