© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 54141
    Prev
    Next
    INDEX
    Explanations

    identifying areas, personalize your

    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_65k_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
     поговорим
    0.45
    셸
    0.43
     달
    0.43
     화
    0.43
     близ
    0.43
    지도
    0.43
     एक्सप्लेन
    0.43
     питание
    0.43
    ЛЯ
    0.42
     민
    0.42
    POSITIVE LOGITS
    }((
    0.45
     hinders
    0.44
    ťa
    0.44
    au
    0.43
    ít
    0.43
     homotopy
    0.41
     hearing
    0.41
    tfrac
    0.41
    VPN
    0.41
     Comprom
    0.41
    Activations Density 0.008%

    No Known Activations