© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48267
    Prev
    Next
    INDEX
    Explanations

    $N_d$ or $T_c$

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    を
    -1.29
    そして
    -1.16
    があり
    -1.13
     prakti
    -1.09
    が
    -1.09
    なので
    -1.05
    子は
    -1.05
    齟
    -1.05
     récolte
    -1.00
    と
    -1.00
    POSITIVE LOGITS
    きち
    1.20
     guadag
    1.09
     posteriore
    1.06
    為に
    1.05
     pomiędzy
    1.02
    D
    1.02
     unimaginable
    0.99
    L
    0.97
     levied
    0.96
     bestimm
    0.95
    Activations Density 0.019%

    No Known Activations