© 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. 50724
    Prev
    Next
    INDEX
    Explanations

    Protein Powerhouses

    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
    விரி
    0.42
    οι
    0.42
    ufthansa
    0.42
    τής
    0.41
    ɥ
    0.41
     балко
    0.41
    𝙪
    0.41
    ुली
    0.40
    }--\
    0.40
    ुका
    0.39
    POSITIVE LOGITS
     it
    0.53
    ↵
    0.51
     this
    0.49
    ↵↵
    0.49
     l
    0.48
     there
    0.46
     O
    0.46
     y
    0.45
     Pokemon
    0.44
     makes
    0.44
    Activations Density 0.000%

    No Known Activations