© 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
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6239
    Prev
    Next
    INDEX
    Explanations

    descriptive words before level

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OTP
    1.32
     washout
    1.24
    pick
    1.24
     disqual
    1.23
     miscellaneous
    1.22
     otp
    1.21
     misfort
    1.20
    误
    1.19
    PICK
    1.17
    ortis
    1.17
    POSITIVE LOGITS
    level
    3.91
     level
    3.84
    levels
    3.83
     levels
    3.64
     nível
    3.48
     livello
    3.42
    Level
    3.40
     LEVEL
    3.36
     Level
    3.30
     LEVELS
    3.29
    Activations Density 0.207%

    No Known Activations