© 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. 84182
    Prev
    Next
    INDEX
    Explanations

    phrases with 'with', 'from', 'for', 'of', 'in'

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

    customized learning paths and innovative approaches

    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
     весьма
    0.64
     sogenannten
    0.61
     довольно
    0.60
    }$.
    0.59
     그것
    0.59
    那种
    0.57
    га
    0.56
    })$.
    0.55
    ielleicht
    0.55
     그
    0.54
    POSITIVE LOGITS
     approx
    0.71
    \
    0.55
     Hwy
    0.53
     HQ
    0.52
     SMD
    0.51
     HDD
    0.51
     vs
    0.50
     (>
    0.50
     including
    0.50
     MSc
    0.49
    Activations Density 0.081%

    No Known Activations