© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 174122
    Prev
    Next
    INDEX
    Explanations

    weight limit

    np_acts-logits-general · gemini-2.5-flash-lite

    overcoming challenges, requires testing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    \...
    0.56
    é
    0.52
     UNDP
    0.51
    ©
    0.51
    уна
    0.50
    ...
    0.49
    …
    0.49
    \
    0.48
    uner
    0.47
    ala
    0.47
    POSITIVE LOGITS
     yağ
    0.54
     değişken
    0.52
     equilíbrio
    0.52
     ağırl
    0.51
     müşter
    0.49
    Balances
    0.48
    מד
    0.48
     எண்ணெய்
    0.47
     hotly
    0.47
    വശ
    0.46
    Activations Density 0.001%

    No Known Activations