© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 131850
    Prev
    Next
    INDEX
    Explanations

    Pokemon pokemon Track Pokemon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     factorización
    0.42
    ⎜
    0.42
     तूती
    0.40
     Marcia
    0.39
    耄
    0.39
     Дер
    0.38
    enciones
    0.38
     entsprechende
    0.38
     условиях
    0.37
    괄
    0.37
    POSITIVE LOGITS
     shoved
    0.41
    מור
    0.41
     Pokemon
    0.40
     pokemon
    0.38
     visita
    0.38
    ]$-
    0.38
     Track
    0.38
    Pokemon
    0.37
     Optional
    0.37
     Proportion
    0.37
    Activations Density 0.000%

    No Known Activations