© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 125574
    Prev
    Next
    INDEX
    Explanations

    Salt, Value, panic

    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_31_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
    ﻬ
    0.55
     excepciones
    0.53
    strate
    0.49
     dedicado
    0.48
     игре
    0.46
    estim
    0.46
     consejos
    0.46
    லுக்கு
    0.46
     ذلك
    0.46
    icus
    0.46
    POSITIVE LOGITS
    K
    0.49
     можуть
    0.44
    Kana
    0.44
     uuid
    0.43
     Cognito
    0.43
    ไม่
    0.42
    Waar
    0.42
    Quando
    0.41
    F
    0.41
    റായി
    0.41
    Activations Density 0.002%

    No Known Activations