© 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. 19749
    Prev
    Next
    INDEX
    Explanations

    already, prior, duration

    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
     questione
    1.00
    ]++;
    1.00
     ===
    0.93
    Dave
    0.92
    丆
    0.92
     lançamento
    0.92
     explotación
    0.91
    龋
    0.90
     thisTrack
    0.90
     revisar
    0.90
    POSITIVE LOGITS
    Already
    0.82
     breeds
    0.81
     already
    0.77
    already
    0.75
     formats
    0.73
     Already
    0.71
     вже
    0.70
    既に
    0.70
    のは
    0.68
     ఇప్పటికే
    0.67
    Activations Density 0.000%

    No Known Activations