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. 31-GEMMASCOPE-2-RES-262K
    4. 35407
    Prev
    Next
    INDEX
    Explanations

    grow slowly

    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
     dokon
    0.52
     miała
    0.49
     finisher
    0.47
     disso
    0.46
    :
    0.46
     বলেছে
    0.45
     tinha
    0.45
    είο
    0.44
     persone
    0.44
    цыя
    0.44
    POSITIVE LOGITS
    *.
    0.40
     Injuries
    0.40
    anders
    0.39
     monumental
    0.38
    rored
    0.38
     *,
    0.37
    BagConstraints
    0.37
     অয়েল
    0.37
     Bacterial
    0.37
     injuries
    0.36
    Activations Density 0.001%

    No Known Activations