© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4179
    Prev
    Next
    INDEX
    Explanations

    answer category numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
     beginning
    1.56
     mot
    1.56
     means
    1.49
     z
    1.48
     old
    1.45
     less
    1.45
     song
    1.44
     ser
    1.43
     not
    1.43
     gets
    1.43
    POSITIVE LOGITS
     teclado
    1.44
    捗
    1.32
    حدى
    1.30
     limitaciones
    1.29
    äjä
    1.28
     crescendo
    1.27
    ěné
    1.25
     experimentos
    1.23
     umana
    1.22
     استاد
    1.22
    Activations Density 0.004%

    No Known Activations