© 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. 26194
    Prev
    Next
    INDEX
    Explanations

    confirming studies and experiments

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

    confirming previous statements

    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
    ิ
    0.49
    ія
    0.48
    过了
    0.47
    і
    0.47
    煊
    0.46
    ול
    0.46
    habitude
    0.46
    ần
    0.46
    િસ્
    0.45
    ፡
    0.45
    POSITIVE LOGITS
     confirm
    0.51
    以及
    0.47
    bio
    0.47
     confirms
    0.47
     microbiological
    0.46
     confirmer
    0.45
     confirmations
    0.45
     PLUS
    0.44
     confirmation
    0.44
     propuestas
    0.44
    Activations Density 0.000%

    No Known Activations