© 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-65K
    7. 56499
    Prev
    Next
    INDEX
    Explanations

    names followed by surnames

    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_65k_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
    .;
    0.55
    .,
    0.54
    для
    0.48
    .:
    0.45
    née
    0.45
    jø
    0.44
    ust
    0.44
    romatic
    0.43
    umento
    0.42
    ơ
    0.42
    POSITIVE LOGITS
     policemen
    0.46
     Estad
    0.40
     Wyman
    0.40
     brotherhood
    0.39
     frère
    0.39
     traffickers
    0.38
     Eros
    0.38
     bodyguard
    0.38
     smugg
    0.38
     technischen
    0.37
    Activations Density 0.004%

    No Known Activations