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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 17028
    Prev
    Next
    INDEX
    Explanations

    through political

    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
     substantiate
    0.62
    Benzoimidazole
    0.51
    CurrentByte
    0.50
    uale
    0.50
     ustal
    0.50
     સામાન્ય
    0.49
    andı
    0.49
    ㄽ
    0.48
    🫢
    0.47
     સે
    0.47
    POSITIVE LOGITS
     rejection
    0.47
    t
    0.45
    род
    0.42
    <0xB1>
    0.41
     bibli
    0.41
    sentiment
    0.40
    PAL
    0.40
     Camps
    0.40
     tacit
    0.39
    is
    0.39
    Activations Density 0.002%

    No Known Activations