© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 8007
    Prev
    Next
    INDEX
    Explanations

    authors' names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
    regation
    1.63
    멤버
    1.59
    arran
    1.58
    iolet
    1.56
    irmed
    1.53
    issau
    1.49
    ริกา
    1.47
    (':
    1.46
     Xeon
    1.46
     Macri
    1.46
    POSITIVE LOGITS
     writing
    2.57
     writer
    2.44
     novelists
    2.36
    小説
    2.36
     novelist
    2.35
     writers
    2.33
     literary
    2.31
    小說
    2.28
     essay
    2.24
     write
    2.22
    Activations Density 0.159%

    No Known Activations