© 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. 35785
    Prev
    Next
    INDEX
    Explanations

    data keys and identifiers

    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
    Dans
    0.43
    this
    0.40
    マ
    0.40
    În
    0.39
    Mga
    0.39
     laughs
    0.37
    ლ
    0.37
    Inte
    0.37
     arti
    0.36
    ພ
    0.36
    POSITIVE LOGITS
     org
    0.48
    IENT
    0.45
     KEY
    0.43
    ENSATION
    0.42
    SACTION
    0.41
     com
    0.41
    ERAL
    0.41
     কিছু
    0.40
     قدم
    0.40
    urn
    0.40
    Activations Density 0.001%

    No Known Activations