© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166761
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by creative output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    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
     zag
    0.38
    AppBar
    0.37
     Valletta
    0.36
     arp
    0.36
    വ
    0.36
    Visit
    0.35
     innov
    0.35
    zungen
    0.35
     cab
    0.35
     tiz
    0.34
    POSITIVE LOGITS
     な
    0.39
     Scholarship
    0.39
     PASSWORD
    0.38
     опасность
    0.38
     próxima
    0.36
    nextLine
    0.36
     Namespace
    0.36
     નામ
    0.36
     Sexuality
    0.36
     artinya
    0.35
    Activations Density 0.001%

    No Known Activations