© 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. 164115
    Prev
    Next
    INDEX
    Explanations

    Gerber Ritchie

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

    Guten Morgen

    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
    縣
    0.53
    𝐛
    0.50
     '*':
    0.49
    时
    0.49
    s
    0.48
     వరు
    0.48
     номера
    0.47
     ကျွန်
    0.47
    funcionario
    0.47
    sü
    0.47
    POSITIVE LOGITS
    <h2>
    0.46
     bumps
    0.46
     Gerber
    0.45
    esor
    0.44
    itchie
    0.44
    াতেই
    0.44
     continuité
    0.44
     loves
    0.43
     thump
    0.43
     Samaritan
    0.43
    Activations Density 0.001%

    No Known Activations