© 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. 163208
    Prev
    Next
    INDEX
    Explanations

    sized dumpster

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

    ChatGPT models

    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
    FindingsResponse
    0.51
    }/>
    0.46
    Manus
    0.46
     যেই
    0.46
    },\\
    0.45
    𒆷
    0.45
    Pref
    0.44
     exile
    0.44
     పిల్ల
    0.44
    }]_{
    0.43
    POSITIVE LOGITS
     açık
    0.49
    amı
    0.46
    με
    0.45
    டுகின்றன
    0.44
     தெரிவித்த
    0.44
    presumably
    0.43
     tùy
    0.43
    感觉
    0.42
    ανο
    0.42
     slalom
    0.42
    Activations Density 0.001%

    No Known Activations