© 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. 7358
    Prev
    Next
    INDEX
    Explanations

    returning None on error

    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
     frm
    1.56
     drafts
    1.48
     Remo
    1.43
     favourites
    1.37
    spaper
    1.36
    כר
    1.34
    緍
    1.34
     Parm
    1.33
    حه
    1.33
     citer
    1.33
    POSITIVE LOGITS
     Moovit
    1.58
    翅
    1.52
    Programs
    1.47
    さえ
    1.45
     energii
    1.45
     dehydrogen
    1.44
    伴
    1.44
     benzoate
    1.41
     famí
    1.40
    躯
    1.39
    Activations Density 0.000%

    No Known Activations