© 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. 228425
    Prev
    Next
    INDEX
    Explanations

    responders

    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
    兰
    0.51
     கட்டி
    0.50
    ﻚ
    0.48
    𝘦
    0.47
    Adap
    0.47
    كو
    0.46
    Vill
    0.46
    LTH
    0.46
    ELO
    0.45
    𝙴
    0.45
    POSITIVE LOGITS
     investor
    0.54
     manipulator
    0.52
     firefighter
    0.52
     director
    0.51
     manipulation
    0.51
     advisor
    0.50
     ascent
    0.50
     divest
    0.50
     rollercoaster
    0.50
     illustrator
    0.49
    Activations Density 0.000%

    No Known Activations