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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 126270
    Prev
    Next
    INDEX
    Explanations

    rhythm ranch

    np_acts-logits-general · gemini-2.5-flash-lite

    freedom of speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     순
    0.50
     이후
    0.50
     계속
    0.50
     했습니다
    0.49
    VerFile
    0.49
     इंपोर्ट
    0.49
     वर्णन
    0.48
     직
    0.48
     걱
    0.48
     상관
    0.48
    POSITIVE LOGITS
    textures
    0.53
    県の
    0.50
    県
    0.49
    縣
    0.47
    Ви
    0.44
    sms
    0.43
    щими
    0.43
    資
    0.43
    در
    0.42
    cms
    0.42
    Activations Density 0.005%

    No Known Activations