© 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-16K
    7. 561
    Prev
    Next
    INDEX
    Explanations

    Jellyfish Kit Thielaviopsis

    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_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
     Mas
    1.38
     Di
    1.36
     k
    1.34
     Ch
    1.33
     MS
    1.33
     Ma
    1.33
     ca
    1.32
     Re
    1.32
     Ot
    1.32
     K
    1.31
    POSITIVE LOGITS
     abaste
    1.57
     investigadores
    1.56
     sustancias
    1.48
     homogé
    1.47
     almacen
    1.41
     muebles
    1.40
     ajustar
    1.40
     edificio
    1.40
     ciudadanos
    1.40
     traslad
    1.39
    Activations Density 1.210%

    No Known Activations