© 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. 40-GEMMASCOPE-2-RES-262K
    7. 214949
    Prev
    Next
    INDEX
    Explanations

    checking df columns or row content

    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_40_width_262k_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
     TCM
    0.44
     age
    0.41
     Santa
    0.40
    opuerto
    0.39
     embarked
    0.38
     mortem
    0.38
     Cait
    0.38
     순
    0.37
     Com
    0.37
     Will
    0.37
    POSITIVE LOGITS
    zeichnungen
    0.43
    そこ
    0.42
    vocabulary
    0.41
    doesn
    0.39
    indeed
    0.38
    subdir
    0.38
     therewith
    0.37
    Vocabulary
    0.37
     vocabulary
    0.36
     opus
    0.36
    Activations Density 0.006%

    No Known Activations