© 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. 71584
    Prev
    Next
    INDEX
    Explanations

    technical or descriptive phrases

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

    relinquishing control

    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
     discordant
    0.56
    𝑪
    0.50
     cambiando
    0.49
     cambió
    0.48
    ियमित
    0.48
    SaveChanges
    0.47
    marital
    0.47
    ㎛
    0.47
    ING
    0.47
    ял
    0.47
    POSITIVE LOGITS
    artists
    0.46
     attrib
    0.41
     Beach
    0.40
     Kru
    0.40
    oyo
    0.39
     BATH
    0.39
     DK
    0.39
     Beleza
    0.38
    especially
    0.38
     UU
    0.38
    Activations Density 0.000%

    No Known Activations