© 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. 149295
    Prev
    Next
    INDEX
    Explanations

    custom rectangle

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

    project setup

    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
    2
    0.52
    Eating
    0.48
    dq
    0.48
    first
    0.47
    core
    0.47
    FIRST
    0.46
    hooting
    0.45
     ersten
    0.44
    Micro
    0.44
    Software
    0.43
    POSITIVE LOGITS
     이어
    0.52
    යි
    0.51
     다른
    0.49
     Allah
    0.49
    ﻙ
    0.48
     DENUMIRE
    0.48
     beneficiaries
    0.47
     Osmanlı
    0.47
     Балт
    0.47
     연결
    0.47
    Activations Density 0.000%

    No Known Activations