© 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
    5. 29-GEMMASCOPE-2-RES-16K
    7. 81
    Prev
    Next
    INDEX
    Explanations

    intensifiers and descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     आहेत
    0.53
    ului
    0.49
    ês
    0.49
    În
    0.49
    esque
    0.48
     possono
    0.47
     seront
    0.47
    ș
    0.47
    方の
    0.47
    Ș
    0.46
    POSITIVE LOGITS
     बहुत
    0.40
     अपनी
    0.40
     अपने
    0.38
     पूरे
    0.37
     오히려
    0.36
     इसके
    0.36
     अपना
    0.35
     यह
    0.35
     कुछ
    0.33
    充分
    0.33
    Activations Density 0.025%

    No Known Activations