© 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. 162695
    Prev
    Next
    INDEX
    Explanations

    announced plans

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

    structuring options after goal

    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
     cyberspace
    0.50
     secreted
    0.48
    əsi
    0.46
     Nevada
    0.46
     operative
    0.45
    閒
    0.45
     consensual
    0.44
    രിക്ക
    0.43
     lawful
    0.43
     euph
    0.43
    POSITIVE LOGITS
    équipe
    0.52
    aso
    0.51
    Tareas
    0.48
    ouwd
    0.47
    Caro
    0.47
    acane
    0.47
    㧕
    0.46
     कैरियर
    0.45
    brat
    0.45
    tsch
    0.45
    Activations Density 0.001%

    No Known Activations