© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 47208
    Prev
    Next
    INDEX
    Explanations

    citations and lists

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

    within a range or time

    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
    খিক
    0.45
    ிய
    0.44
     المالية
    0.44
    ﻛ
    0.43
    ियार
    0.43
    ওর
    0.42
    ];//
    0.42
    𝙩
    0.42
    ቂያ
    0.42
    แย
    0.42
    POSITIVE LOGITS
     agon
    0.49
     navegar
    0.46
     colonized
    0.44
     agonizing
    0.43
     characterized
    0.42
    ainted
    0.42
     ascribe
    0.42
     wondrous
    0.41
     devemos
    0.41
     scarred
    0.41
    Activations Density 0.000%

    No Known Activations