© 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. 98250
    Prev
    Next
    INDEX
    Explanations

    utilization rate and banana bread

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

    technical infrastructure and components

    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
     পারছি
    0.46
     抗
    0.46
     Advance
    0.45
    ﻑ
    0.44
    㫜
    0.44
    攘
    0.44
    মান
    0.42
    Ax
    0.41
     Mighty
    0.41
    ０
    0.40
    POSITIVE LOGITS
     కె
    0.49
     shamb
    0.45
    చ్
    0.43
     neon
    0.43
    љено
    0.41
    សុ
    0.41
     demoral
    0.40
     motivator
    0.40
     gimbal
    0.40
     thorac
    0.40
    Activations Density 0.002%

    No Known Activations