© 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. 24060
    Prev
    Next
    INDEX
    Explanations

    tie sanctions

    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
     مح
    0.35
    liet
    0.31
     перечис
    0.31
    ․
    0.31
     אחר
    0.31
    肌
    0.31
    ષ
    0.30
    "{@
    0.30
     본격
    0.30
     மேலே
    0.30
    POSITIVE LOGITS
     it
    0.48
     ilyen
    0.41
     hacerlo
    0.40
     esso
    0.39
     উহা
    0.38
     solchen
    0.38
    它可以
    0.38
     melakukannya
    0.37
     slike
    0.36
     sådan
    0.36
    Activations Density 0.043%

    No Known Activations