© 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-RES-262K
    7. 21623
    Prev
    Next
    INDEX
    Explanations

    day or step plans

    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_31_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
     of
    0.64
     with
    0.60
     is
    0.55
     before
    0.52
    な
    0.51
     cellules
    0.51
     habitually
    0.50
    の
    0.50
    ת
    0.50
     positifs
    0.50
    POSITIVE LOGITS
     Affair
    0.45
    ponent
    0.41
    ෙන්ම
    0.41
    long
    0.40
    Break
    0.39
    anamh
    0.38
     Roadmap
    0.38
    break
    0.38
    Fence
    0.38
     अनिवार
    0.38
    Activations Density 0.029%

    No Known Activations