© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 8523
    Prev
    Next
    INDEX
    Explanations

    what is possible

    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_16_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
    ुल
    0.74
    که
    0.66
    俚
    0.64
    od
    0.63
    မှတ်
    0.59
     çocuğ
    0.59
    ﺪ
    0.59
    定め
    0.58
     कोर्स
    0.57
    I
    0.57
    POSITIVE LOGITS
     impossible
    0.91
     l
    0.80
    il
    0.79
    на
    0.68
     dari
    0.68
     Raila
    0.68
    an
    0.65
     v
    0.64
     imposs
    0.64
    Impossible
    0.62
    Activations Density 0.019%

    No Known Activations