© 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. 227248
    Prev
    Next
    INDEX
    Explanations

    monitored phone

    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
     presentation
    0.50
     advertising
    0.47
     samping
    0.47
     retention
    0.47
    presentation
    0.47
    advert
    0.46
    advertising
    0.45
     .
    0.45
     side
    0.45
     cabel
    0.45
    POSITIVE LOGITS
    ૩
    0.55
    нести
    0.54
     répar
    0.53
    Ꮡ
    0.52
    ᴙ
    0.51
    项
    0.51
     ግራም
    0.50
    ૄ
    0.48
    太阳
    0.47
    }]$.
    0.47
    Activations Density 0.001%

    No Known Activations