© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2957
    Prev
    Next
    INDEX
    Explanations

    phrasal verbs for action and change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_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
    Don
    0.95
    Attack
    0.95
    W
    0.89
    Guide
    0.89
    Down
    0.88
    Delta
    0.88
    Reason
    0.87
    guide
    0.84
    Spe
    0.82
    M
    0.82
    POSITIVE LOGITS
    ListArr
    1.00
     dwRes
    0.95
     fists
    0.95
     vending
    0.94
     Turing
    0.91
     cheeks
    0.91
     custList
    0.91
     LOCCTR
    0.90
     myWeb
    0.90
     eyeballs
    0.90
    Activations Density 0.051%

    No Known Activations