© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-65K
    4. 3198
    Prev
    Next
    INDEX
    Explanations

    direct access and actions

    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
    {
    1.38
    _
    1.28
    ги
    1.14
    )$
    1.12
    }
    1.12
    RE
    1.10
    ية
    1.10
     große
    1.07
    }_
    1.05
     étend
    1.05
    POSITIVE LOGITS
    t
    1.33
    s
    1.25
     Direct
    1.22
    the
    1.20
     direct
    1.19
    direct
    1.17
    directly
    1.15
    i
    1.13
     Directly
    1.13
     مستقیم
    1.09
    Activations Density 0.167%

    No Known Activations