© 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-65K
    7. 62834
    Prev
    Next
    INDEX
    Explanations

    almost + descriptive word

    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
    ,)
    0.42
    )
    0.42
    ),
    0.41
     Corporations
    0.38
    annuation
    0.38
    .)
    0.38
     گفته
    0.38
    ?.
    0.37
     Potomac
    0.37
    ým
    0.37
    POSITIVE LOGITS
    Swift
    0.47
    chine
    0.47
    Goed
    0.46
    Ƙ
    0.45
     parthenogenetic
    0.45
     decolor
    0.45
    Chromatic
    0.44
     situazione
    0.44
     fungal
    0.44
    চ্ছিন্ন
    0.44
    Activations Density 0.004%

    No Known Activations