© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 6034
    Prev
    Next
    INDEX
    Explanations

    verb followed by direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
    iyeti
    1.06
    ɧ
    1.00
    ))=
    0.98
    сног
    0.97
     }=
    0.96
    geojson
    0.96
    عنوان
    0.95
    ))+
    0.95
    uras
    0.93
    ただし
    0.92
    POSITIVE LOGITS
     الحال
    1.10
     பழ
    0.98
     Rheumat
    0.94
     jeweils
    0.93
     Anfield
    0.93
     évaluations
    0.93
     Bite
    0.92
     стол
    0.91
     Už
    0.91
     entail
    0.90
    Activations Density 0.016%

    No Known Activations