© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4881
    Prev
    Next
    INDEX
    Explanations

    writing sentences

    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
    1.67
     makeSound
    1.67
    츠
    1.54
    arten
    1.51
    afin
    1.51
    athione
    1.51
    쾌
    1.50
    irti
    1.49
     combust
    1.48
    <end_of_image>
    1.48
    POSITIVE LOGITS
     nombreux
    1.51
     شام
    1.46
    hoea
    1.44
     nets
    1.44
     prawns
    1.43
     peninsula
    1.38
     organisers
    1.33
     pediatrician
    1.31
     Evidence
    1.31
     crocodiles
    1.30
    Activations Density 0.011%

    No Known Activations