© 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. 106756
    Prev
    Next
    INDEX
    Explanations

    renters, alternatives, area

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

    public domain

    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
    木
    0.46
    B
    0.45
    Et
    0.45
     Attribute
    0.45
    ექ
    0.45
     Et
    0.43
    中
    0.42
     Seasonal
    0.42
     Attempts
    0.42
    С
    0.42
    POSITIVE LOGITS
     י
    0.51
     riesgo
    0.49
     лига
    0.48
     fidèle
    0.48
    resse
    0.48
     bảy
    0.47
     traslad
    0.47
     numberWithFloat
    0.47
     pertenece
    0.46
     الخمسه
    0.46
    Activations Density 0.001%

    No Known Activations