© 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. 16-GEMMASCOPE-2-RES-65K
    7. 2419
    Prev
    Next
    INDEX
    Explanations

    link with or links to

    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_16_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
    0
    1.08
    يد
    1.00
    يل
    0.98
    ០
    0.96
    ري
    0.93
    <0x80>
    0.91
    }$:
    0.90
    }\
    0.89
    يف
    0.89
    }")
    0.88
    POSITIVE LOGITS
    d
    1.42
    ल
    1.20
    n
    1.13
    م
    1.13
    У
    1.13
     to
    1.09
    त
    1.05
     with
    1.03
     connections
    1.03
    g
    1.03
    Activations Density 0.569%

    No Known Activations