© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 2103
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
    i
    0.89
     двумя
    0.88
    ことで
    0.85
    вная
    0.79
    רים
    0.77
     materias
    0.77
     thisobject
    0.76
    ﻨ
    0.75
    日英
    0.75
     месяц
    0.73
    POSITIVE LOGITS
     atteindre
    0.89
     arrivée
    0.84
    équ
    0.79
     enfants
    0.76
     évol
    0.75
     augmenter
    0.74
     Ajouter
    0.74
     opérateurs
    0.72
     opérateur
    0.71
     télé
    0.70
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.