© 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. 177897
    Prev
    Next
    INDEX
    Explanations

    home and office contexts

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

    commercial spaces

    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
    <unused57>
    0.53
    ENDMENT
    0.52
     τότε
    0.51
    <unused27>
    0.48
    <unused41>
    0.47
    ICATION
    0.46
    EDUCATION
    0.46
    ITERATURE
    0.46
     compreensão
    0.46
     ਤੁਸੀਂ
    0.46
    POSITIVE LOGITS
    Sac
    0.45
    s
    0.45
     unit
    0.44
    back
    0.44
    ped
    0.43
    script
    0.43
     Sauv
    0.43
    San
    0.43
     LP
    0.42
    poner
    0.42
    Activations Density 0.001%

    No Known Activations