© 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. 3425
    Prev
    Next
    INDEX
    Explanations

    advice, tips, strategies

    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
    rinsic
    1.72
    imitives
    1.64
     combust
    1.52
    Diffuse
    1.51
    7
    1.48
    basically
    1.44
    了起来
    1.43
     playable
    1.42
    º
    1.40
     autonomic
    1.39
    POSITIVE LOGITS
     consejos
    1.86
     consiglio
    1.79
     conseils
    1.63
     biographer
    1.60
    タック
    1.58
    她在
    1.56
    سى
    1.53
     strategist
    1.52
     mistakes
    1.51
     fréquente
    1.51
    Activations Density 0.128%

    No Known Activations