Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 372
    Prev
    Next
    INDEX
    Explanations

    to + verb or phrase

    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_40_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
     Segmentation
    0.21
     அதற்கு
    0.21
    tica
    0.20
     Markers
    0.19
     Techniques
    0.19
    }^
    0.19
     Weighted
    0.19
     Remaining
    0.19
     Mitochond
    0.19
    **.
    0.18
    POSITIVE LOGITS
    ppled
    0.44
    ffee
    0.39
    ppling
    0.39
     be
    0.37
     appease
    0.37
     improve
    0.36
    pless
    0.36
     alleviate
    0.36
     survive
    0.36
     accompany
    0.35
    Activations Density 0.090%

    No Known Activations