© 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. 144067
    Prev
    Next
    INDEX
    Explanations

    Maya snapped

    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
    ing
    0.51
     書き
    0.44
     significative
    0.43
    </strong>
    0.42
    }"
    0.40
    ao
    0.40
    dim
    0.40
     Morph
    0.39
     मालम
    0.39
    edel
    0.39
    POSITIVE LOGITS
    ހ
    0.47
     swells
    0.44
    sick
    0.44
     quenching
    0.43
     congested
    0.43
     quench
    0.43
     drums
    0.42
     dries
    0.42
     strains
    0.42
    Together
    0.41
    Activations Density 0.005%

    No Known Activations