© 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. 4000
    Prev
    Next
    INDEX
    Explanations

    phrases that mean i didn't mean to

    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
    startIndex
    1.17
    3
    1.14
    asant
    1.09
    триму
    1.07
    跖
    1.07
     competing
    1.06
    pole
    1.05
    height
    1.04
     classify
    1.04
    _{-
    1.04
    POSITIVE LOGITS
     Appliance
    1.40
     appliances
    1.34
     Appliances
    1.27
     appliance
    1.22
     comforts
    1.16
     pleasures
    1.13
     diagnostics
    1.07
    贈り物
    1.06
     revelations
    1.04
     Geschenk
    1.04
    Activations Density 0.051%

    No Known Activations