© 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. 45741
    Prev
    Next
    INDEX
    Explanations

    domain name, House Speaker, individualistic

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

    private branches

    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
    有问题
    0.49
    ：
    0.47
    었던
    0.46
     overhe
    0.46
    :
    0.45
     başlayan
    0.44
    غيرة
    0.44
    ન્
    0.44
     ဟ
    0.43
    AutoScaleMode
    0.43
    POSITIVE LOGITS
    lysis
    0.45
     노력
    0.45
    rural
    0.44
     Rural
    0.44
    prits
    0.44
     Ghar
    0.44
     행동
    0.42
    linking
    0.42
    ាត់
    0.41
    clusters
    0.41
    Activations Density 0.000%

    No Known Activations