© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11405
    Prev
    Next
    INDEX
    Explanations

    explaining why something is good

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
     nn
    2.91
    ும்
    2.89
    PURE
    2.88
    Reco
    2.87
    ==============]
    2.68
    ினார்கள்
    2.53
    限于
    2.52
     thảo
    2.46
    CNT
    2.46
    酐
    2.42
    POSITIVE LOGITS
    houette
    2.78
    வை
    2.71
    दारा
    2.62
    ər
    2.62
    iflower
    2.57
    waukee
    2.53
    مه
    2.50
     بیٹ
    2.46
    نهار
    2.46
    మర్శ
    2.40
    Activations Density 0.018%

    No Known Activations