© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 15509
    Prev
    Next
    INDEX
    Explanations

    severity of infection

    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
    ioane
    0.49
     worksheets
    0.48
    喡
    0.44
    СТЬ
    0.44
    вы
    0.44
    ქვს
    0.43
    LETE
    0.43
    GoString
    0.43
    ﻥ
    0.43
    Calc
    0.42
    POSITIVE LOGITS
     Land
    0.48
     Nacional
    0.46
     Okay
    0.45
     Island
    0.45
     
    0.45
     Positive
    0.44
    سكرية
    0.44
     Strateg
    0.44
     Dire
    0.43
     Negara
    0.43
    Activations Density 0.001%

    No Known Activations