© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 19763
    Prev
    Next
    INDEX
    Explanations

    groupId in XML tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
     adjunction
    0.86
    വിധ
    0.85
    賏
    0.81
    aneers
    0.81
    ફો
    0.80
    വദ
    0.79
     Feuilles
    0.79
    Ś
    0.78
     अकाउंट
    0.78
    फोल
    0.77
    POSITIVE LOGITS
    டெ
    0.70
    ố
    0.66
     Scratch
    0.66
     Home
    0.65
    니까
    0.63
     pens
    0.62
    pe
    0.62
    /*'
    0.60
     and
    0.60
     Rem
    0.60
    Activations Density 0.000%

    No Known Activations