© 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. 3593
    Prev
    Next
    INDEX
    Explanations

    visualizations and descriptions

    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
    !
    1.37
    哦
    1.37
    False
    1.32
     correctamente
    1.25
    able
    1.20
     dependiendo
    1.20
    True
    1.17
    示す
    1.15
    !'
    1.15
    蟄
    1.14
    POSITIVE LOGITS
     Sketch
    1.44
     sf
    1.44
     Szer
    1.43
     Daf
    1.42
     Conversations
    1.41
     Beratung
    1.40
     alleys
    1.36
     marg
    1.35
     alley
    1.35
     LR
    1.33
    Activations Density 0.030%

    No Known Activations