© 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. 42108
    Prev
    Next
    INDEX
    Explanations

    Kurzgesagt and 3Blue1Brown explanations

    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
     endast
    0.42
     disciplina
    0.41
     pouze
    0.41
     ancak
    0.41
    posti
    0.40
    服
    0.40
     hijas
    0.39
     proč
    0.39
    잭
    0.39
     افراد
    0.39
    POSITIVE LOGITS
     liquefied
    0.47
     liquef
    0.44
     Energy
    0.42
     油
    0.42
     Sparkling
    0.42
     Toshiba
    0.41
     https
    0.41
     References
    0.40
     Beverages
    0.40
     http
    0.39
    Activations Density 0.004%

    No Known Activations