© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136275
    Prev
    Next
    INDEX
    Explanations

    single, control, lambda

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     $>
    0.52
     तिवारी
    0.50
    }$
    0.50
     مثال
    0.48
    י
    0.48
     الحي
    0.48
     экологи
    0.48
    risch
    0.47
    {\
    0.47
    ฟ
    0.46
    POSITIVE LOGITS
    ﮕ
    0.57
    ಬ್ಬಿಣ
    0.56
    Ę
    0.48
    ificazione
    0.46
     chargés
    0.45
    ÊN
    0.43
    EN
    0.43
    ಂಬ
    0.42
     carri
    0.42
     reticulum
    0.42
    Activations Density 0.000%

    No Known Activations