© 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. 40-GEMMASCOPE-2-RES-262K
    7. 119331
    Prev
    Next
    INDEX
    Explanations

    solving for variable

    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
     j
    0.38
     s
    0.37
     d
    0.36
     geeft
    0.35
    iff
    0.35
     ;
    0.35
    RL
    0.35
     gives
    0.35
     防
    0.35
     u
    0.34
    POSITIVE LOGITS
     практике
    0.38
    त्रेयी
    0.37
    㥳
    0.37
    🦐
    0.37
    bowl
    0.36
     টালি
    0.36
    धानिक
    0.36
     चाहिये
    0.36
    🕺
    0.36
    ्याच्या
    0.35
    Activations Density 0.025%

    No Known Activations