© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 31545
    Prev
    Next
    INDEX
    Explanations

    flame forgiveness, VPN tunnel

    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
    ∨
    0.44
     грун
    0.43
    ীব্র
    0.40
     blaming
    0.39
    сква
    0.39
     shitty
    0.38
    ButtonBar
    0.38
     toe
    0.38
    ♢
    0.38
     fucked
    0.37
    POSITIVE LOGITS
    icana
    0.40
    zahl
    0.39
    monitoring
    0.39
    ú
    0.38
    imi
    0.38
     exits
    0.37
    ido
    0.37
    urn
    0.36
     management
    0.36
     sledge
    0.36
    Activations Density 0.000%

    No Known Activations