© 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. 27561
    Prev
    Next
    INDEX
    Explanations

    python print statements

    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
     estimated
    0.49
     Estimated
    0.41
     dye
    0.40
     tin
    0.39
    fullscreen
    0.39
    ",(
    0.39
    ]"
    0.38
     '#
    0.38
    !("{}",
    0.38
    ffiche
    0.36
    POSITIVE LOGITS
    Bran
    0.44
     सरफेस
    0.39
     एनिमल
    0.39
    کروچ
    0.38
    ਇ
    0.38
    Hydroxy
    0.38
    Characteristics
    0.37
     ライン
    0.37
     Bran
    0.36
     प्योर
    0.36
    Activations Density 0.005%

    No Known Activations