© 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. 220593
    Prev
    Next
    INDEX
    Explanations

    physical objects or locations

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

    misunderstanding, need a

    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
    mph
    0.52
     связанных
    0.47
    Გ
    0.46
    aison
    0.46
    م
    0.45
    หาคม
    0.45
    জে
    0.44
    coh
    0.44
     Honors
    0.44
    䀖
    0.43
    POSITIVE LOGITS
     dive
    0.54
     blue
    0.51
     blau
    0.49
     jogos
    0.49
     poodle
    0.49
     tummy
    0.48
     toxic
    0.48
     dusk
    0.48
     pain
    0.47
     vontade
    0.47
    Activations Density 0.002%

    No Known Activations