© 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. 29881
    Prev
    Next
    INDEX
    Explanations

    becoming supported

    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
    আনু
    0.46
    ᐋ
    0.44
    ര്‍ഷ
    0.44
    mathspace
    0.44
    omethane
    0.43
    আনুশকা
    0.43
    不允许
    0.42
    ികിത്സ
    0.42
     İli
    0.42
    Certification
    0.42
    POSITIVE LOGITS
    ので
    0.47
     SMAD
    0.46
    0.46
    ,[
    0.45
     persuade
    0.45
    :
    0.44
     ineffective
    0.43
    *
    0.43
     стран
    0.42
     desarrolla
    0.42
    Activations Density 0.004%

    No Known Activations