© 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. 111249
    Prev
    Next
    INDEX
    Explanations

    animals dancing, AWS ami

    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
     Strom
    0.43
    沇
    0.43
     misinformation
    0.41
     Eis
    0.41
    َنْ
    0.41
     speculative
    0.40
    Indust
    0.39
    ्यावर
    0.39
     Our
    0.39
     Life
    0.38
    POSITIVE LOGITS
    itherto
    0.54
    யின்
    0.46
     Акысыз
    0.45
    })]
    0.45
    vecb
    0.45
     акысыз
    0.45
    },
    0.44
     hérit
    0.42
     aquella
    0.41
     nächsten
    0.41
    Activations Density 0.002%

    No Known Activations