© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 4467
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and connected nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     locales
    0.33
    Spending
    0.33
    Circ
    0.33
    Sincerely
    0.33
    Bri
    0.32
    Responsible
    0.31
    gebung
    0.31
    '
    0.31
     Herbs
    0.31
    Sc
    0.31
    POSITIVE LOGITS
     eyes
    0.44
     ouders
    0.43
     knuckles
    0.42
     yeux
    0.41
     ears
    0.40
     parents
    0.39
     lèvres
    0.39
     oncologist
    0.39
    beatCounter
    0.39
     occhi
    0.38
    Activations Density 0.139%

    No Known Activations