© 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. 74881
    Prev
    Next
    INDEX
    Explanations

    blocs tilted

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

    creates stability

    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
    eng
    0.51
    uchen
    0.50
    odge
    0.49
    itelji
    0.49
    <0x97>
    0.48
    ро
    0.47
    ді
    0.46
    ✸
    0.45
    ко
    0.45
    ੩
    0.45
    POSITIVE LOGITS
     visitas
    0.55
     inoc
    0.52
     indígenas
    0.50
     ilusión
    0.49
     arranque
    0.49
     urgente
    0.47
     increment
    0.46
     supermerc
    0.46
     showrooms
    0.46
     bouncy
    0.46
    Activations Density 0.001%

    No Known Activations