© 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. 42048
    Prev
    Next
    INDEX
    Explanations

    avoiding negative outcomes

    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
     Į
    0.47
    ْل
    0.46
    ́ch
    0.46
    ्ह
    0.46
    ছুর
    0.45
     Vý
    0.44
    ്‍
    0.44
     ŝ
    0.44
    𝟰
    0.44
     Cuando
    0.43
    POSITIVE LOGITS
     generally
    0.52
    .
    0.42
    ’
    0.41
     libertarian
    0.40
     unlikely
    0.40
     considers
    0.39
     broadly
    0.38
     rhetorical
    0.38
    inguistic
    0.38
     outsourcing
    0.38
    Activations Density 0.005%

    No Known Activations