© 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. 31-GEMMASCOPE-2-RES-262K
    7. 30095
    Prev
    Next
    INDEX
    Explanations

    public services, access

    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_31_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
    縮
    0.42
     sart
    0.41
    缛
    0.41
     Teut
    0.40
    筞
    0.40
    창
    0.40
     провер
    0.39
     eyelids
    0.39
     сокра
    0.38
    க்கார
    0.38
    POSITIVE LOGITS
    ’
    0.50
    ih
    0.49
    blic
    0.47
     services
    0.47
     umož
    0.46
     gwar
    0.46
     permettant
    0.46
     palvel
    0.46
    ien
    0.45
    ochi
    0.45
    Activations Density 0.002%

    No Known Activations