© 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. 15-GEMMASCOPE-2-RES-16K
    7. 2283
    Prev
    Next
    INDEX
    Explanations

    diffusion and learning processes

    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_15_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
     Oph
    0.97
     Bonne
    0.85
     Endocrinology
    0.85
     Erskine
    0.84
     Hammond
    0.84
    稅
    0.83
     Rhodesia
    0.82
     Paraguay
    0.81
     Osc
    0.80
     Africa
    0.80
    POSITIVE LOGITS
     grout
    1.37
     regener
    1.18
    簇
    1.13
     radicals
    1.10
    tul
    1.10
     Rimini
    1.09
     pulsed
    1.09
     Koy
    1.09
    regener
    1.09
    Rad
    1.08
    Activations Density 0.328%

    No Known Activations