© 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. 28179
    Prev
    Next
    INDEX
    Explanations

    quoting and reporting speech

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

    want to

    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
    ：
    0.54
    d
    0.50
    riss
    0.47
    0.47
    ですが
    0.45
    コミ
    0.44
    が行
    0.44
    不明
    0.43
    standalone
    0.43
    r
    0.42
    POSITIVE LOGITS
     கூறி
    0.56
     कहकर
    0.55
     ಎಂದು
    0.53
     opção
    0.53
    ﻮ
    0.52
     possibilità
    0.50
     ಸೂಚ
    0.50
     possibilidade
    0.50
     intentos
    0.50
     esforços
    0.50
    Activations Density 0.002%

    No Known Activations