© 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. 99716
    Prev
    Next
    INDEX
    Explanations

    statement, inaccurate, incomplete

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

    important, controls, electric

    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
    Mere
    0.44
    Fif
    0.43
    ytte
    0.43
    0.43
    wonderful
    0.43
    uose
    0.42
    erer
    0.42
    yka
    0.41
    G
    0.41
     ವಿಶ
    0.41
    POSITIVE LOGITS
     promulg
    0.51
     sıv
    0.51
    病情
    0.50
     نقص
    0.50
     kötü
    0.49
    酩
    0.47
     geliştir
    0.46
    疼痛
    0.44
     narcot
    0.44
     narc
    0.44
    Activations Density 0.007%

    No Known Activations