© 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. 16-GEMMASCOPE-2-RES-262K
    7. 86714
    Prev
    Next
    INDEX
    Explanations

    searchable internet audio

    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_16_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
    ᱐
    0.54
     лица
    0.51
    woven
    0.50
     hapless
    0.50
    colored
    0.50
     கரிம
    0.49
     آپ
    0.49
     miserable
    0.48
     ово
    0.48
    mau
    0.48
    POSITIVE LOGITS
     B
    0.63
     AES
    0.55
     VIA
    0.54
     CEC
    0.53
     IEC
    0.52
     Region
    0.51
     LGBTQ
    0.51
    ه
    0.51
    نه
    0.51
    บ
    0.50
    Activations Density 0.000%

    No Known Activations