© 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. 15509
    Prev
    Next
    INDEX
    Explanations

    on the description

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

    severity of infection

    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
    ioane
    0.49
     worksheets
    0.46
    ﻥ
    0.46
     iod
    0.44
    ຫວ
    0.44
    લાક
    0.44
    喡
    0.42
    вы
    0.42
     EXAMPLE
    0.42
    СТЬ
    0.42
    POSITIVE LOGITS
     Ass
    0.48
    }
    0.47
     Land
    0.47
    سكرية
    0.47
     Nacional
    0.45
     Okay
    0.44
     Dire
    0.44
     Kend
    0.44
    }([
    0.44
    }+
    0.43
    Activations Density 0.000%

    No Known Activations