© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9686
    Prev
    Next
    INDEX
    Explanations

    personal experiences

    np_acts-logits-general · gemini-2.5-flash-lite

    asking me to do something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    on
    0.50
    os
    0.48
     unseren
    0.43
    ার
    0.42
    V
    0.42
    我们
    0.41
    minist
    0.41
    timed
    0.41
    MIN
    0.40
    er
    0.40
    POSITIVE LOGITS
    ſelf
    0.46
     persönlich
    0.46
     sceptical
    0.41
     के
    0.40
     の
    0.40
     realist
    0.40
     ก
    0.38
    谘
    0.38
     deus
    0.38
    ियस
    0.38
    Activations Density 0.387%

    No Known Activations