© 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. 9-GEMMASCOPE-2-RES-16K
    7. 2349
    Prev
    Next
    INDEX
    Explanations

    love followed by other words

    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_9_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
    ר
    3.17
    isées
    2.51
    ி
    2.47
    чни
    2.43
    }".
    2.42
     illegally
    2.39
     Mathf
    2.37
    ivní
    2.36
    াপি
    2.33
    एस
    2.32
    POSITIVE LOGITS
    د
    3.90
    bigcirc
    2.85
    casa
    2.76
     tabulation
    2.74
     surely
    2.73
     ayudas
    2.73
    adding
    2.71
    al
    2.71
    ோம்
    2.70
     ſh
    2.69
    Activations Density 0.203%

    No Known Activations