© 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. 2077
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives followed by clauses

    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
     [[
    0.65
     similar
    0.65
     both
    0.58
     [(
    0.57
     not
    0.56
     used
    0.54
     estimated
    0.54
     believed
    0.53
     better
    0.53
     common
    0.53
    POSITIVE LOGITS
    hender
    0.71
    faced
    0.64
    stepping
    0.64
    -
    0.62
    jumping
    0.59
     embl
    0.59
    leaning
    0.58
    giver
    0.58
    blooded
    0.58
    heartedly
    0.58
    Activations Density 0.401%

    No Known Activations