© 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. 1404
    Prev
    Next
    INDEX
    Explanations

    unspecified skills, medals, or risk

    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
     stakeholders
    0.51
    THRESHOLD
    0.48
    াড়াও
    0.47
     NOL
    0.47
     threshold
    0.46
    ントリー
    0.46
     필요
    0.45
    샬
    0.45
     volumes
    0.45
    ړو
    0.44
    POSITIVE LOGITS
    in
    0.51
     Ancient
    0.48
    ẩm
    0.47
     அதிகரிக்கிறது
    0.47
     noirâtre
    0.46
    ifaiFace
    0.45
     folos
    0.45
     parvenir
    0.44
     belir
    0.44
    bet
    0.44
    Activations Density 0.013%

    No Known Activations