© 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. 11084
    Prev
    Next
    INDEX
    Explanations

    limerick about

    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
    醛
    2.63
     FontWeight
    2.62
    ્લે
    2.62
    ponin
    2.59
    šću
    2.53
    ї
    2.52
    ॉर्क
    2.47
     Alfvén
    2.46
    窕
    2.44
    ynomial
    2.44
    POSITIVE LOGITS
    வெளி
    2.42
    обходимо
    2.31
    ECC
    2.18
    indic
    2.18
    ion
    2.13
     southwest
    2.10
    aard
    2.09
    ikr
    2.09
    ified
    2.09
    ும்
    2.08
    Activations Density 0.014%

    No Known Activations