© 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. 31-GEMMASCOPE-2-RES-262K
    7. 143255
    Prev
    Next
    INDEX
    Explanations

    authority said

    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
     curioso
    0.41
     kilka
    0.40
     transcription
    0.39
     molecular
    0.39
     deposited
    0.39
    <sup>
    0.38
    inyl
    0.38
     sufrido
    0.38
    <sub>
    0.38
     transmitted
    0.38
    POSITIVE LOGITS
    㩽
    0.47
     образование
    0.46
    txtbtn
    0.44
    真正的
    0.42
    最後
    0.42
     झालं
    0.42
    汋
    0.42
     राहि
    0.41
    ణం
    0.40
    未来
    0.40
    Activations Density 0.009%

    No Known Activations