© 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. 202372
    Prev
    Next
    INDEX
    Explanations

    College and rain

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

    each half

    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
     Исто
    0.56
     تأ
    0.53
     ፍ
    0.53
     Сколько
    0.53
    內
    0.50
     ან
    0.50
     отобра
    0.49
     Въ
    0.48
     उदाहरण
    0.47
     შეს
    0.47
    POSITIVE LOGITS
    仔
    0.48
    adina
    0.44
    WAM
    0.43
    жок
    0.42
     certes
    0.42
    ggak
    0.41
    たっぷ
    0.40
    ग्गा
    0.40
    oodle
    0.40
    واج
    0.40
    Activations Density 0.000%

    No Known Activations