© 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-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 3595
    Prev
    Next
    INDEX
    Explanations

    holographic simulation or projection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ிய
    0.96
    uksi
    0.93
     venture
    0.87
    )
    0.87
    érateur
    0.84
    尽可能
    0.83
     considérable
    0.82
     Saltar
    0.82
    ).
    0.82
    ţiei
    0.82
    POSITIVE LOGITS
    س
    1.31
    s
    1.18
    رو
    1.08
    ش
    1.07
    ER
    0.97
     supernatants
    0.96
    ن
    0.95
    sik
    0.93
    ড
    0.93
    LEN
    0.92
    Activations Density 0.083%

    No Known Activations